Triple
T29776371
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Consorzio Tutela Pecorino Toscano DOP |
E755388
|
entity |
| Predicate | hasProtectedProduct |
P87853
|
FINISHED |
| Object | Pecorino Toscano PDO cheese |
E207974
|
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: Pecorino Toscano PDO cheese | Statement: [Consorzio Tutela Pecorino Toscano DOP, hasProtectedProduct, Pecorino Toscano PDO cheese]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasProtectedProduct Context triple: [Consorzio Tutela Pecorino Toscano DOP, hasProtectedProduct, Pecorino Toscano PDO cheese]
-
A.
isProtectedFor
Indicates that one entity is safeguarded or preserved specifically for the benefit, use, or rights of another entity.
-
B.
isProtectedFrom
Indicates that one entity is safeguarded or shielded against harm, damage, or adverse effects caused by another entity or factor.
-
C.
hasProtectionPurpose
Indicates that something is intended or designed to serve a protective function or goal.
-
D.
isProtectedBy
Indicates that one entity provides protection, defense, or safeguarding for another entity.
-
E.
protectsProductType
chosen
Indicates that one entity provides protection or safeguarding specifically for a certain type or category of product.
- F. None of above.
Provenance (4 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_69f0ef878574819088c867fd1a5c8b86 |
completed | April 28, 2026, 5:33 p.m. |
| NER | Named-entity recognition | batch_69ff9bed58dc8190a204816d4ed6c32c |
completed | May 9, 2026, 8:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a2713fc476881909be8b437895bd5e8 |
completed | June 8, 2026, 7:11 p.m. |
| PD | Predicate disambiguation | batch_69ff9b69653c81908ab0d88055a66a88 |
completed | May 9, 2026, 8:39 p.m. |
Created at: April 28, 2026, 8:46 p.m.