Triple
T25300930
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Evian negotiations |
E634341
|
entity |
| Predicate | primaryFrenchLeader |
P113859
|
FINISHED |
| Object | Charles de Gaulle |
—
|
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: Charles de Gaulle | Statement: [Evian negotiations, primaryFrenchLeader, Charles de Gaulle]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryFrenchLeader Context triple: [Evian negotiations, primaryFrenchLeader, Charles de Gaulle]
-
A.
notableLeaderFrance
chosen
Indicates that the subject is recognized as a notable leader associated with France.
-
B.
monarchOfFrance
Indicates that one entity holds the position or title of monarch (king or queen) of France in relation to another entity.
-
C.
monarchOfFrenchSide
Indicates that one entity serves as the ruling monarch over the French side or faction in a given context or domain.
-
D.
royalistLeader
Indicates that one entity is the leader of a royalist faction, movement, or cause in relation to another entity.
-
E.
lastCapetianKingOfFrance
Indicates that the subject is the final monarch of France belonging to the Capetian royal dynasty.
- 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_69e75a972c6481909bc11710e8d30a6c |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f757898fe48190b124dc7301672623 |
completed | May 3, 2026, 2:11 p.m. |
| PD | Predicate disambiguation | batch_69f754c484348190948d2a04ff228fb1 |
completed | May 3, 2026, 1:59 p.m. |
Created at: April 21, 2026, 1:24 p.m.