Triple
T18418485
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Khanaspur Campus |
E441956
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Khanaspur |
—
|
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: Khanaspur | Statement: [Khanaspur Campus, locatedIn, Khanaspur]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Khanaspur Context triple: [Khanaspur Campus, locatedIn, Khanaspur]
-
A.
Khanaspur
chosen
Khanaspur is a small hill station and tourist resort in Pakistan’s Galyat region, known for its cool climate, forested slopes, and scenic mountain views.
-
B.
Khanpur
Khanpur is a prominent town in Rajasthan, India, known as one of the key urban centers of Jhalawar district.
-
C.
Khanpur
Khanpur is a residential neighborhood in South East Delhi, India, known for its urban character and proximity to major city routes and markets.
-
D.
Khanpur
Khanpur is a significant urban and commercial center in southern Punjab, Pakistan, known for its agricultural trade and regional connectivity.
-
E.
Rajanpur
Rajanpur is a city in Pakistan known as an administrative and commercial center in the southern part of Punjab province.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b9eb8a508190a942fd75ebd8b1dc |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e51a2a0fb08190b409ed200a9d86a6 |
completed | April 19, 2026, 6:08 p.m. |
Created at: April 10, 2026, 10:47 a.m.