Triple
T8540859
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NBO |
E202189
|
entity |
| Predicate | servesAsFocusCityFor |
P1655
|
FINISHED |
| Object | Fly540 |
E371537
|
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: Fly540 | Statement: [NBO, servesAsFocusCityFor, Fly540]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fly540 Context triple: [NBO, servesAsFocusCityFor, Fly540]
-
A.
Fly540 (some operations)
chosen
Fly540 (some operations) is a Kenyan low-cost airline that operates regional passenger services within East Africa.
-
B.
Travel Air 5000
The Travel Air 5000 was a late-1920s American high-wing monoplane airliner and mailplane known for its role in early commercial aviation and long-distance flights.
-
C.
IFLY
IFLY is the airline callsign used by IndiGo, a major low-cost carrier based in India.
-
D.
Flightplan
Flightplan is a 2005 psychological thriller film starring Jodie Foster as a mother whose daughter mysteriously disappears during a transatlantic flight.
-
E.
Voli
Voli is a Montenegrin retail company best known for operating one of the country’s largest supermarket and hypermarket chains.
- 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_69ca832461e88190a654c5e44e233aa8 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe6e10bc081909a7210c577b807fb |
completed | March 31, 2026, 3:23 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ce6da3d65c819087ed6b46dfc35885 |
completed | April 2, 2026, 1:22 p.m. |
Created at: March 30, 2026, 6:18 p.m.