Triple
T36527181
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Château Tour Léognan (white) |
E900337
|
entity |
| Predicate | classificationOfEstate |
P187001
|
FINISHED |
| Object | Graves Grand Cru Classé |
—
|
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: Graves Grand Cru Classé | Statement: [Château Tour Léognan (white), classificationOfEstate, Graves Grand Cru Classé]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: classificationOfEstate Context triple: [Château Tour Léognan (white), classificationOfEstate, Graves Grand Cru Classé]
-
A.
hasEstateType
Indicates that an entity possesses or is associated with a particular category or type of estate.
-
B.
numberOfClassifiedEstates
Indicates the count of estates that have been formally classified or categorized in a given context.
-
C.
countryEstateType
Indicates the classification or category of an estate based on the country in which it is located or to which it belongs.
-
D.
heirOfEstate
Indicates that one entity is legally designated to inherit the estate or property of another entity, typically upon that entity’s death.
-
E.
partOfEstate
Indicates that something belongs to, is included within, or forms a component of a particular estate (such as a legal or property estate).
- F. None of above. chosen
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_69f76e5eedb88190a393b8c623f71dd7 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fb2e940d5c8190bceae77daf4ef512 |
completed | May 6, 2026, 12:05 p.m. |
| PD | Predicate disambiguation | batch_69f9fec70bd881909c658a3c5020318b |
completed | May 5, 2026, 2:29 p.m. |
| PDg | Predicate description generation | batch_69fb2e9309fc81909dfefd9020d6fbad |
completed | May 6, 2026, 12:05 p.m. |
Created at: May 3, 2026, 4:11 p.m.