Triple
T31954983
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arnaud Decagny |
E815878
|
entity |
| Predicate | positionHeldInCountry |
P126851
|
FINISHED |
| Object | mayor in 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: mayor in France | Statement: [Arnaud Decagny, positionHeldInCountry, mayor in France]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: positionHeldInCountry Context triple: [Arnaud Decagny, positionHeldInCountry, mayor in France]
-
A.
positionHeldInJurisdiction
chosen
Indicates that an entity holds or has held a specific position, office, or role within a particular legal or geographic jurisdiction.
-
B.
positionHeld
Indicates that an entity occupies or has occupied a specific role, job, office, or position within an organization or context.
-
C.
positionHeldUnder
Indicates that one entity holds or held a specific position, office, or role under the authority, administration, or jurisdiction of another entity.
-
D.
currentHolderCountry
Indicates the country that currently possesses, controls, or holds the referenced entity.
-
E.
locatedInTheCountryOfOffice
Indicates that an office or organizational branch is situated within the specified country.
- 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_69f348f4ec708190abbb2a7c3ed58844 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69fe9dfaa2d08190b2084f63f842eb6b |
completed | May 9, 2026, 2:37 a.m. |
| PD | Predicate disambiguation | batch_69fe9bba947c81908b0b2b92a4d19b37 |
completed | May 9, 2026, 2:28 a.m. |
Created at: May 1, 2026, 12:08 a.m.