term disambiguation
From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-09.)
term disambiguation has 20 facts recorded in Dontopedia across 3 references, with 3 live disagreements.
Mostly:step(5), sequence(5), uses(3)
Maturity scale
raw canonical shape-checked rule-derived certifiedOther facts (19)
The long tail: predicates that appear too rarely to warrant their own section. Filter or scroll to find a specific one. Each row links to its source.
| Predicate | Value | Ref |
|---|---|---|
| Step | Split Query | [1] |
| Step | Generate Embedding | [1] |
| Step | Compare Embeddings | [1] |
| Step | Select Closest Match | [1] |
| Step | Append Match | [1] |
| Sequence | Split Query | [1] |
| Sequence | Generate Embedding | [1] |
| Sequence | Compare Embeddings | [1] |
| Sequence | Select Closest Match | [1] |
| Sequence | Append Match | [1] |
| Uses | Bert System | [1] |
| Uses | Context | [3] |
| Uses | Knowledge Graph | [3] |
| Rdf:type | Process | [1] |
| Compares Embeddings | Term Vs Candidate | [2] |
| Builds Context String | Joined Context | [2] |
| Result | Disambiguated Term | [3] |
| Iterates Over | Individual Terms | [3] |
| Uses Context | Query Context | [3] |
Timeline
Timeline axis is valid_time — when each source says the fact was true in the world, not when Dontopedia learned about it. Retracted rows are kept for provenance; coloured stripes indicate the context kind.
References (3)
ctx:claims/beam/b6b0b011-2ea9-48ce-a85b-83edabc260d3- full textbeam-chunktext/plain1 KB
doc:beam/b6b0b011-2ea9-48ce-a85b-83edabc260d3Show excerpt
disambiguated_terms.append(closest_match) else: disambiguated_terms.append(term) # Join the disambiguated terms back into a single string disambiguated_query = " ".join(disambiguated…
ctx:claims/beam/1adff1c9-94a8-4376-92a8-08bd968e378c- full textbeam-chunktext/plain1 KB
doc:beam/1adff1c9-94a8-4376-92a8-08bd968e378cShow excerpt
# Average the embeddings of the term tokens if term_start is not None and term_end is not None: term_embedding = last_hidden_state[:, term_start:term_end, :].mean(dim=1) else: term_embedding = torch.zeros((1…
ctx:claims/beam/104f47d4-b023-450e-90a1-1989f29e2feb- full textbeam-chunktext/plain803 B
doc:beam/104f47d4-b023-450e-90a1-1989f29e2febShow excerpt
disambiguated_query = disambiguate_terms(query) print(disambiguated_query) ``` ### Explanation 1. **Entity Linking**: - Define a function `find_entity_linking` to find the most relevant entity for the ambiguous term using a knowledge g…
See also
Keep researching
Missing something or suspicious of what's here? Kick off a research session — a Claude agent will investigate, cite its sources, and file new facts into a dedicated context you can review before accepting into the shared view.