Triple
T29500182
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nechirvan Barzani |
E748343
|
entity |
| Predicate | capitalOfRegionServed |
P3877
|
FINISHED |
| Object | Erbil |
—
|
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: Erbil | Statement: [Nechirvan Barzani, capitalOfRegionServed, Erbil]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: capitalOfRegionServed Context triple: [Nechirvan Barzani, capitalOfRegionServed, Erbil]
-
A.
countryCapitalOfRegionServed
Indicates that a country is the capital or primary governing center of the specified region it serves.
-
B.
capitalOfCountryServed
Indicates that a city serves as the capital of a given country.
-
C.
capitalOfReferencedRegion
Indicates that one entity serves as the capital city or administrative center of the region referenced by another entity.
-
D.
capitalCityOfRegion
chosen
Indicates that a city serves as the official capital of a specified region, functioning as its primary administrative or governmental center.
-
E.
capitalOfRegionLocatedHere
Indicates that a place serves as the capital of a region that is geographically located at or associated with this place.
- 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_69f0bd455a9c8190b40a3e8ea38cf61f |
completed | April 28, 2026, 1:59 p.m. |
| NER | Named-entity recognition | batch_69f791cc969c8190bf187d6031a030d5 |
completed | May 3, 2026, 6:19 p.m. |
| PD | Predicate disambiguation | batch_69f791033d288190b118029fe412b9c9 |
completed | May 3, 2026, 6:16 p.m. |
Created at: April 28, 2026, 4:22 p.m.