Triple
T24886115
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Koinawa Village |
E622855
|
entity |
| Predicate | isPartOfCountryRegion |
P38421
|
FINISHED |
| Object | Gilbert Islands group of Kiribati |
—
|
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: Gilbert Islands group of Kiribati | Statement: [Koinawa Village, isPartOfCountryRegion, Gilbert Islands group of Kiribati]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isPartOfCountryRegion Context triple: [Koinawa Village, isPartOfCountryRegion, Gilbert Islands group of Kiribati]
-
A.
isRegion
Indicates that one entity functions as a geographic or administrative region associated with another entity.
-
B.
isRegionOf
chosen
Indicates that one entity is a geographic or administrative region belonging to, contained within, or associated with another entity.
-
C.
inCountrySubregion
Indicates that one location or entity is situated within a specific subregion of a country.
-
D.
hasPartInCountry
Indicates that an entity has a component, section, or portion that is located within a specified country.
-
E.
countryOrRegion
Indicates that one entity is a country or geographic region associated with another entity (such as its location, jurisdiction, or area of relevance).
- 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_69e2fac4aa848190b3446a3922cec150 |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f61f12b0f08190bc4a16907941864c |
completed | May 2, 2026, 3:58 p.m. |
| PD | Predicate disambiguation | batch_69f61b37a5648190b10d33ae205ccfee |
completed | May 2, 2026, 3:41 p.m. |
Created at: April 18, 2026, 5:25 a.m.