Triple
T18959783
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bhikhiwind tehsil |
E463881
|
entity |
| Predicate | hasSettlement |
P1068
|
FINISHED |
| Object | Bhikhiwind |
—
|
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: Bhikhiwind | Statement: [Bhikhiwind tehsil, hasSettlement, Bhikhiwind]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bhikhiwind Context triple: [Bhikhiwind tehsil, hasSettlement, Bhikhiwind]
-
A.
Bhikhiwind
chosen
Bhikhiwind is a small border town in the Indian state of Punjab, known for its proximity to the India–Pakistan border and for being the hometown of Sarabjit Singh.
-
B.
Bohooth
Bohooth is a metro station on Cairo Metro Line 2 serving passengers in the Greater Cairo area.
-
C.
Baydhaba
Baydhaba is a major city in southwestern Somalia that serves as the capital of the Bay region and an important political and commercial center.
-
D.
Bhirkot
Bhirkot is a town and former village development committee located in Syangja District of Gandaki Province in central Nepal.
-
E.
Ghinghinda
Ghinghinda is a rural locality within Queensland’s Banana Shire, known for its agricultural and pastoral landscape.
- 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_69d8dcffc278819086792a4ebfddfafa |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d5d1d784819095f3f886d7c47175 |
completed | April 20, 2026, 7:29 a.m. |
Created at: April 10, 2026, noon