Triple
T1487529
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Celebic–South Halmahera languages |
E29500
|
entity |
| Predicate | arealContext |
P3227
|
FINISHED |
| Object | eastern Indonesia |
—
|
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: eastern Indonesia | Statement: [Celebic–South Halmahera languages, arealContext, eastern Indonesia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: arealContext Context triple: [Celebic–South Halmahera languages, arealContext, eastern Indonesia]
-
A.
arealFeature
Indicates a relationship where something is characterized as a spatial or geographic feature occupying an area on a surface or map.
-
B.
arealRegion
Indicates that something occupies or pertains to a specific two-dimensional geographic or spatial area.
-
C.
geographicContext
chosen
Indicates that one entity is situated within, associated with, or characterized by the geographic setting or region defined by another entity.
-
D.
arealRelation
Indicates a spatial relationship between areas, such as overlap, containment, adjacency, or relative positioning between two regions.
-
E.
placesInContext
Indicates that one entity situates, interprets, or frames another entity within a particular context or surrounding circumstances.
- 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_69a498da82e08190ba833330d05f380f |
completed | March 1, 2026, 7:51 p.m. |
| NER | Named-entity recognition | batch_69a4c6a44efc819084254614d8ea4669 |
completed | March 1, 2026, 11:07 p.m. |
| PD | Predicate disambiguation | batch_69a4c486eacc81909c272f9bdf50a7c3 |
completed | March 1, 2026, 10:58 p.m. |
Created at: March 1, 2026, 8:12 p.m.