Triple
T31329030
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | General council of France |
E798973
|
entity |
| Predicate | successorBodyNameChangeEffectiveDate |
P149084
|
FINISHED |
| Object | March 2015 |
—
|
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: March 2015 | Statement: [General council of France, successorBodyNameChangeEffectiveDate, March 2015]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: successorBodyNameChangeEffectiveDate Context triple: [General council of France, successorBodyNameChangeEffectiveDate, March 2015]
-
A.
nameChangeDate
Indicates the date on which an entity’s name was officially changed.
-
B.
administrativeChangeDate
Indicates the date on which an administrative change (such as an update, modification, or reclassification) affecting the entity was officially recorded or took effect.
-
C.
successorNameInUseSince
chosen
Indicates that the successor’s name has been actively used starting from a specified point in time.
-
D.
admittedSuccessorEntityDate
Indicates the date on which a successor entity was formally admitted or recognized as taking over from a predecessor.
-
E.
supersededByDate
Indicates the date on which something is replaced or rendered obsolete by a newer version or successor.
- 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_69f224e3238c8190b2291f50ea4962cd |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69fef3ceef648190b58027c93d757438 |
completed | May 9, 2026, 8:43 a.m. |
| PD | Predicate disambiguation | batch_69fef359da2c819091a034387b08821f |
completed | May 9, 2026, 8:42 a.m. |
Created at: April 29, 2026, 9:16 p.m.