Triple
T3811712
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Duke of Richelieu |
E93150
|
entity |
| Predicate | officeHeldByTitleHolder |
P45587
|
FINISHED |
| Object | Chief Minister of France |
—
|
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: Chief Minister of France | Statement: [Duke of Richelieu, officeHeldByTitleHolder, Chief Minister of France]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: officeHeldByTitleHolder Context triple: [Duke of Richelieu, officeHeldByTitleHolder, Chief Minister of France]
-
A.
officeHeldOf
chosen
Indicates that a specific office or position is (or was) held by a particular person or entity.
-
B.
officeHeldUnder
Indicates that one entity holds or has held an official position, role, or office under the authority, jurisdiction, or administration of another entity.
-
C.
officeHeldByMember
Indicates that a specific office or position is held or occupied by a particular member.
-
D.
officeHeldDuring
Indicates that a person occupied a specific official position during a particular time period.
-
E.
officeHeldTogetherWith
Indicates that two or more individuals simultaneously held the same office or position during an overlapping period.
- 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_69aed96a60088190ab1df8390fffc935 |
completed | March 9, 2026, 2:30 p.m. |
| NER | Named-entity recognition | batch_69aef1515c688190a38332aedeed8a76 |
completed | March 9, 2026, 4:12 p.m. |
| PD | Predicate disambiguation | batch_69aee7482d708190a3ec74745b102a4c |
completed | March 9, 2026, 3:29 p.m. |
Created at: March 9, 2026, 3:16 p.m.