Triple
T36051055
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Darbuk |
E1042808
|
entity |
| Predicate | infrastructureTypeNearby |
P124983
|
FINISHED |
| Object | military roads |
—
|
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: military roads | Statement: [Darbuk, infrastructureTypeNearby, military roads]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: infrastructureTypeNearby Context triple: [Darbuk, infrastructureTypeNearby, military roads]
-
A.
infrastructureNearby
Indicates that one entity is located close to another entity that serves as infrastructure (such as roads, utilities, or public facilities).
-
B.
hasNearbyInfrastructureType
chosen
Indicates that an entity is located close to infrastructure of a specified type.
-
C.
nearbyFacilityType
Indicates that a facility of a specified type is located close to a given reference entity or location.
-
D.
transportationNearby
Indicates that there is a transportation facility or service located close to the referenced entity.
-
E.
hasNearbyLandUse
Indicates that one land area is located close to another area characterized by a specific type of land use.
- 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_69f76e2e41f8819091f9fb0536920fec |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7b2c771108190adeec151daad5dab |
completed | May 3, 2026, 8:40 p.m. |
| PD | Predicate disambiguation | batch_69f7b1bad2e88190963ab4ee5d4f2038 |
completed | May 3, 2026, 8:36 p.m. |
Created at: May 3, 2026, 4:07 p.m.