Triple
T7834591
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jodhpur Airport |
E181658
|
entity |
| Predicate | locatedInTimeZone |
P109
|
FINISHED |
| Object | Asia/Kolkata |
E5066
|
NE 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: Asia/Kolkata | Statement: [Jodhpur Airport, locatedInTimeZone, Asia/Kolkata]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Asia/Kolkata Context triple: [Jodhpur Airport, locatedInTimeZone, Asia/Kolkata]
-
A.
Indian Standard Time
chosen
Indian Standard Time is the time zone used throughout India, set at UTC+5:30.
-
B.
Indian Ocean Time
Indian Ocean Time is a time zone used by several territories in the Indian Ocean region, including islands and coastal areas.
-
C.
Bangladesh Standard Time
Bangladesh Standard Time is the time zone used in Bangladesh, corresponding to UTC+6 hours with no daylight saving time.
-
D.
Afghanistan Time
Afghanistan Time is the standard time zone used throughout Afghanistan, set at UTC+4:30.
-
E.
Madras Time
Madras Time was a former local time standard used in the Madras (now Chennai) region of India before the adoption of a unified national time zone.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca8284a25c8190a1a20afad30da792 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb064b872081908e269f4fe1b85436 |
completed | March 30, 2026, 11:24 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cb5a9b7bb081909d6aa066ee064093 |
completed | March 31, 2026, 5:24 a.m. |
Created at: March 30, 2026, 4:45 p.m.