Triple
T28048548
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Giscard d’Estaing family |
E708753
|
entity |
| Predicate | hasMemberInInstitution |
P2227
|
FINISHED |
| Object | French National Assembly |
—
|
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: French National Assembly | Statement: [Giscard d’Estaing family, hasMemberInInstitution, French National Assembly]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMemberInInstitution Context triple: [Giscard d’Estaing family, hasMemberInInstitution, French National Assembly]
-
A.
hasInstitutions
Indicates that one entity possesses, contains, or is associated with one or more institutions.
-
B.
associatedWithInstitution
chosen
Indicates that an entity has a formal or recognized connection or affiliation with an institution.
-
C.
includesInstitution
Indicates that one entity contains, encompasses, or has as a member a particular institution.
-
D.
hasInstitutionalHome
Indicates that an entity is formally based in, hosted by, or affiliated with a particular institution as its organizational home.
-
E.
hasPrimaryInstitutionType
Indicates that an entity’s main or principal institutional classification or category is of a specified type.
- 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_69ef9b6df9f48190bbb971d02cbe1b65 |
completed | April 27, 2026, 5:22 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. |
Created at: April 27, 2026, 8:31 p.m.