Triple
T3871074
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Prefect of Saint Pierre and Miquelon |
E91985
|
entity |
| Predicate | hasOfficialTitleInFrench |
P51323
|
FINISHED |
| Object | Préfet de Saint-Pierre-et-Miquelon |
—
|
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: Préfet de Saint-Pierre-et-Miquelon | Statement: [Prefect of Saint Pierre and Miquelon, hasOfficialTitleInFrench, Préfet de Saint-Pierre-et-Miquelon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasOfficialTitleInFrench Context triple: [Prefect of Saint Pierre and Miquelon, hasOfficialTitleInFrench, Préfet de Saint-Pierre-et-Miquelon]
-
A.
officialTitleInLanguage
chosen
Indicates that an entity’s official title or designation is expressed in a specified language.
-
B.
hasOfficialNameInEnglish
Indicates that an entity has an officially recognized name expressed in the English language.
-
C.
equivalentTitleInFrench
Indicates that one entity’s title is the equivalent or corresponding title of another entity, specifically expressed in French.
-
D.
nameInFrench
Indicates that an entity is known or referred to by a specific name expressed in the French language.
-
E.
hasOfficialNameInJapanese
Indicates that an entity has an official, formally recognized name expressed in the Japanese language.
- 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_69aed9645f348190a9868e7cef56ab7e |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aeec54b0848190a8d4a0e4df7b6227 |
completed | March 9, 2026, 3:50 p.m. |
| PD | Predicate disambiguation | batch_69aee754dddc8190936e1f9c40a770db |
completed | March 9, 2026, 3:29 p.m. |
Created at: March 9, 2026, 3:20 p.m.