Triple
T19269549
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Basse-Terrien |
E481883
|
entity |
| Predicate | associatedTerritoryType |
P89934
|
FINISHED |
| Object | French overseas region |
—
|
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: French overseas region | Statement: [Basse-Terrien, associatedTerritoryType, French overseas region]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedTerritoryType Context triple: [Basse-Terrien, associatedTerritoryType, French overseas region]
-
A.
associatedTitleTerritory
Indicates a relationship where a specific title is linked or connected to a particular territory or domain.
-
B.
recognizedTerritory
Indicates that one entity formally acknowledges another entity’s claim of authority or ownership over a specific geographic area.
-
C.
relatedTerritory
chosen
Indicates that one territory has a specified relationship or association with another territory.
-
D.
refersToTerritory
Indicates that one entity designates, mentions, or is associated with a specific geographic area or territorial domain.
-
E.
regionallyAssociatedWith
Indicates that two entities are connected or related based on sharing the same or overlapping geographic or regional context.
- 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_69d8e8ce54cc8190998418ff1f66ef28 |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e5fbb74ec48190a58d96b4b5b9af00 |
completed | April 20, 2026, 10:11 a.m. |
| PD | Predicate disambiguation | batch_69e4dd07a7208190afcd51ba1dc87c33 |
completed | April 19, 2026, 1:47 p.m. |
Created at: April 10, 2026, 1:29 p.m.