Triple
T27480480
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | FR-90 |
E693582
|
entity |
| Predicate | hasSubdivisionNameInFrench |
P114757
|
FINISHED |
| Object | Territoire de Belfort |
—
|
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: Territoire de Belfort | Statement: [FR-90, hasSubdivisionNameInFrench, Territoire de Belfort]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSubdivisionNameInFrench Context triple: [FR-90, hasSubdivisionNameInFrench, Territoire de Belfort]
-
A.
subdivisionNameFrench
chosen
Indicates the French-language name assigned to a specific administrative or geographic subdivision.
-
B.
hasOfficialFrenchName
Indicates that an entity possesses an officially recognized name in the French language.
-
C.
subdivisionNameLanguage
Indicates the language in which the name of a subdivision (such as a region, district, or administrative unit) is expressed.
-
D.
hasSubdivisionName3
Indicates that an entity has a third-level subdivision whose name is given by the associated value.
-
E.
hasSubdivisionLabel
Indicates that an entity assigns a specific label or name to one of its subdivisions or component parts.
- 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_69ef5381f2648190a2392d0fab833095 |
completed | April 27, 2026, 12:16 p.m. |
| NER | Named-entity recognition | batch_69fba2877b248190a974eb092243c0c4 |
completed | May 6, 2026, 8:20 p.m. |
| PD | Predicate disambiguation | batch_69fb8d06a1b48190a937aa410d159dfa |
completed | May 6, 2026, 6:48 p.m. |
Created at: April 27, 2026, 12:59 p.m.