Triple
T9178896
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Torta del Casar |
E220269
|
entity |
| Predicate | mainCoagulatingAgent |
P74139
|
FINISHED |
| Object | vegetable rennet |
—
|
LITERAL 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: vegetable rennet | Statement: [Torta del Casar, mainCoagulatingAgent, vegetable rennet]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mainCoagulatingAgent Context triple: [Torta del Casar, mainCoagulatingAgent, vegetable rennet]
-
A.
coagulationAgent
chosen
Indicates that one entity serves as or contains a substance that promotes or causes the coagulation (clotting or thickening) of another entity.
-
B.
coagulationType
Indicates the specific kind or category of coagulation process or method associated with an entity.
-
C.
fermentationAgent
Indicates that one entity serves as the agent or catalyst that carries out the fermentation process on another entity.
-
D.
isThickenedWith
Indicates that one substance has been made more viscous or dense by adding another substance that serves as a thickening agent.
-
E.
enzymeType
Indicates the specific class or category of enzyme associated with an entity or reaction.
- F. None of above.
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_69ca83e589948190ac9907819db11ddf |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69ccc25064588190856c96b229d9cd60 |
completed | April 1, 2026, 6:59 a.m. |
| PD | Predicate disambiguation | batch_69cc66090e5881908889dc1213815626 |
completed | April 1, 2026, 12:25 a.m. |
Created at: March 30, 2026, 7:23 p.m.