Triple
T28535207
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Malé city centre |
E722144
|
entity |
| Predicate | capitalOfCountryCentre |
P135987
|
FINISHED |
| Object | Maldives |
—
|
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: Maldives | Statement: [Malé city centre, capitalOfCountryCentre, Maldives]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: capitalOfCountryCentre Context triple: [Malé city centre, capitalOfCountryCentre, Maldives]
-
A.
capitalOftenLocatedIn
Indicates that the capital city of a region or country is frequently, though not always, situated within a particular location or type of area.
-
B.
administrativeCentreLocatedOn
Indicates that the administrative centre of a region or jurisdiction is situated on or directly adjacent to a specified geographic feature or location.
-
C.
capitalLocation
Indicates the relationship in which a place serves as the capital city or administrative center of a given political or geographic entity.
-
D.
endPointIsCapitalOf
chosen
Indicates that the endpoint entity serves as the capital city of the other related entity (typically a country, state, or region).
-
E.
administrativeCentreType
Indicates the specific kind or level of administrative center that a place serves as within an administrative hierarchy.
- 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_69f01a5d7ec88190ada2d5be7c06c35d |
completed | April 28, 2026, 2:24 a.m. |
| NER | Named-entity recognition | batch_69f71996e1a48190ac59a1d66d7c44e8 |
completed | May 3, 2026, 9:47 a.m. |
| PD | Predicate disambiguation | batch_69f71820c6c88190ab38b4fa626d22cc |
completed | May 3, 2026, 9:40 a.m. |
Created at: April 28, 2026, 3:31 a.m.