Triple
T3197703
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chennai International Airport |
E66972
|
entity |
| Predicate | focusCityFor |
P164
|
FINISHED |
| Object | Air India |
E100865
|
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: Air India | Statement: [Chennai International Airport, focusCityFor, Air India]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Air India Context triple: [Chennai International Airport, focusCityFor, Air India]
-
A.
Air India
chosen
Air India is the flag carrier airline of India, operating domestic and international flights across numerous destinations worldwide.
-
B.
SpiceJet
SpiceJet is a major Indian low-cost airline operating extensive domestic and regional international services.
-
C.
Vistara
Vistara is an Indian full-service airline known for its premium in-flight experience and joint venture ownership by Tata Group and Singapore Airlines.
-
D.
IndiGo
IndiGo is a major Indian low-cost airline known for its extensive domestic network, high on-time performance, and large fleet of Airbus A320-family aircraft.
-
E.
Batik Air
Batik Air is an Indonesian full-service airline operating domestic and regional flights as part of the Lion Air Group.
- 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_69ad8588ba18819086a10951c32ecb80 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada7192994819084817307065a25e2 |
completed | March 8, 2026, 4:43 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b24bb7cd488190ae95c140d9cda296 |
completed | March 12, 2026, 5:14 a.m. |
Created at: March 8, 2026, 3:07 p.m.