Triple
T988266
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gloucester |
E21326
|
entity |
| Predicate | hasTwinTown |
P919
|
FINISHED |
| Object | Gouda |
E70496
|
NE FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Gouda | Statement: [Gloucester, hasTwinTown, Gouda]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gouda Context triple: [Gloucester, hasTwinTown, Gouda]
-
A.
Gouda
chosen
Gouda is a historic Dutch city renowned worldwide for its namesake cheese, traditional cheese market, and well-preserved medieval architecture.
-
B.
Munster cheese
Munster cheese is a strong-smelling, soft cow’s milk cheese from eastern France, especially known for its washed rind and pungent, tangy flavor.
-
C.
Cheshire cheese
Cheshire cheese is a traditional, crumbly British cow's milk cheese from the county of Cheshire, known as one of England's oldest recorded cheese varieties.
-
D.
Bega
Bega is a rural town in New South Wales, Australia, best known as a major dairy and cheese-producing centre.
-
E.
Black Forest ham
Black Forest ham is a traditional German dry-cured, smoked ham from the Black Forest region, prized for its dark exterior, distinctive smoky flavor, and protected regional designation.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69a493c383dc8190a03257f22d4b4183 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b4a89a58819081a24b5b0a12f122 |
completed | March 1, 2026, 9:50 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ac258b55908190bc5bbf1c2756482d |
completed | March 7, 2026, 1:18 p.m. |
Created at: March 1, 2026, 7:41 p.m.