Triple
T23934524
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nakhchivan International Airport |
E602593
|
entity |
| Predicate | hasPushpinMapLocation |
P36479
|
FINISHED |
| Object | Azerbaijan |
—
|
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: Azerbaijan | Statement: [Nakhchivan International Airport, hasPushpinMapLocation, Azerbaijan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPushpinMapLocation Context triple: [Nakhchivan International Airport, hasPushpinMapLocation, Azerbaijan]
-
A.
hasLocationComponent
Indicates that something includes, is associated with, or is composed of a specific location-related part or element.
-
B.
hasAnchorLocation
Indicates that one entity serves as the fixed reference or attachment point (anchor) for the location or position of another entity.
-
C.
hasCheckInLocation
Indicates that an entity performs or is associated with a check-in action at a specific location.
-
D.
mapLocation
chosen
Indicates a relationship where an entity is associated with a specific position or area on a map.
-
E.
hasLocationFocus
Indicates that the primary emphasis or relevance of something is centered on a specific location or 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_69e2953cf6e081909b8e25a10a52dddc |
completed | April 17, 2026, 8:17 p.m. |
| NER | Named-entity recognition | batch_69f1cf9da9c4819085880c6ad521d7ed |
completed | April 29, 2026, 9:30 a.m. |
| PD | Predicate disambiguation | batch_69f16151ebdc819086e9e1d7cc1f4f3c |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 9 p.m.