Triple
T12424363
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Iraq–Turkey border |
E296859
|
entity |
| Predicate | hasEthnicRegion |
P72539
|
FINISHED |
| Object | Kurdish-inhabited areas |
—
|
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: Kurdish-inhabited areas | Statement: [Iraq–Turkey border, hasEthnicRegion, Kurdish-inhabited areas]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasEthnicRegion Context triple: [Iraq–Turkey border, hasEthnicRegion, Kurdish-inhabited areas]
-
A.
belongsToEthnographicRegion
Indicates that an entity is associated with or situated within a specific ethnographic region defined by shared cultural or ethnic characteristics.
-
B.
hasEthnicDivision
Indicates that a group, region, or entity is characterized by internal divisions or distinctions based on ethnicity.
-
C.
isInEthnicState
Indicates that an entity exists within or is governed by a political state defined primarily by a specific ethnic group.
-
D.
holderEthnicity
Indicates the ethnic background or group to which the holder of something (e.g., a document, account, or item) belongs.
-
E.
ethnoLinguisticRegionOf
chosen
Indicates that a region is defined or characterized by the shared ethnic and linguistic identity of the group associated with it.
- 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_69d6ada0640c81908c061d7fb3d47786 |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d94e1888b48190bd750f839a26e99e |
completed | April 10, 2026, 7:23 p.m. |
| PD | Predicate disambiguation | batch_69d94d354b488190adc83fb4f2770dd5 |
completed | April 10, 2026, 7:19 p.m. |
Created at: April 8, 2026, 9:55 p.m.