Triple
T19029609
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roquefort-sur-Soulzon |
E465699
|
entity |
| Predicate | cheeseMilkSource |
P85046
|
FINISHED |
| Object | Lacaune sheep |
—
|
NE NERFINISHED |
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: Lacaune sheep | Statement: [Roquefort-sur-Soulzon, cheeseMilkSource, Lacaune sheep]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lacaune sheep Context triple: [Roquefort-sur-Soulzon, cheeseMilkSource, Lacaune sheep]
-
A.
Lacaune sheep
chosen
Lacaune sheep are a French dairy breed renowned for their rich milk, which is traditionally used to produce Roquefort cheese.
-
B.
Basco-Béarnaise sheep
The Basco-Béarnaise sheep is a traditional dairy breed from the French Pyrenees, valued for its rich milk used in making artisanal cheeses.
-
C.
Manchega sheep
Manchega sheep are a Spanish breed of dairy sheep from the La Mancha region, best known as the traditional source of milk for Manchego cheese.
-
D.
Manech sheep
Manech sheep are a hardy dairy breed from the Pyrenees in southwestern France, best known for producing the milk used in traditional Basque and Béarn cheeses.
-
E.
Romney sheep
Romney sheep are a hardy British long-wool sheep breed known for their adaptability to wet, marshy conditions and for producing heavy fleeces and quality meat.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8dd0359648190bc2a9202c5cf29d2 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d73f98dc81909acbb366f00d2d54 |
completed | April 20, 2026, 7:35 a.m. |
Created at: April 10, 2026, 12:02 p.m.