Triple
T26569903
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New Zealand territory |
E666792
|
entity |
| Predicate | containsOverseasTerritory |
P646
|
FINISHED |
| Object | Tokelau |
—
|
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: Tokelau | Statement: [New Zealand territory, containsOverseasTerritory, Tokelau]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: containsOverseasTerritory Context triple: [New Zealand territory, containsOverseasTerritory, Tokelau]
-
A.
hasOverseasTerritory
chosen
Indicates that one entity possesses or controls a territory located outside its own primary geographic or sovereign domain.
-
B.
containsOverseasRegionOrCollectivity
Indicates that an entity includes within its jurisdiction or composition at least one overseas region or collectivity.
-
C.
overseasCountry
Indicates that one entity is a country located outside the primary or reference country associated with the other entity.
-
D.
hasOverseasPresenceIn
Indicates that an entity maintains operations, offices, or activities in a foreign country or region.
-
E.
overseasRegionOf
Indicates that one region is an overseas territory or administrative division belonging to another country or primary region.
- 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_69ee9cfa21c081909e4e36e087debfc6 |
completed | April 26, 2026, 11:17 p.m. |
| NER | Named-entity recognition | batch_69f7c29e1b848190b945c6c6120a5330 |
completed | May 3, 2026, 9:48 p.m. |
| PD | Predicate disambiguation | batch_69f7c1b6e7a881908deb96bedb2713f4 |
completed | May 3, 2026, 9:44 p.m. |
Created at: April 27, 2026, 1:57 a.m.