Triple
T35676447
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | HP |
E1030872
|
entity |
| Predicate | operatorFoundedAsAirline |
P87805
|
FINISHED |
| Object | America West Airlines |
—
|
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: America West Airlines | Statement: [HP, operatorFoundedAsAirline, America West Airlines]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: operatorFoundedAsAirline Context triple: [HP, operatorFoundedAsAirline, America West Airlines]
-
A.
underlyingCompanyFoundedAsAirline
chosen
Indicates that the underlying company was originally established as an airline.
-
B.
airlineFoundedAs
Indicates that one airline was originally established or created under a particular initial name, structure, or predecessor airline.
-
C.
airlineFoundedAsYear
Indicates the year in which an airline was originally founded under its initial identity or name.
-
D.
airlineFormerName
Indicates that an airline previously operated under a different name, specifying its former official designation.
-
E.
dateRebrandedAsCapitalAirlines
Indicates that an entity’s date corresponds to when an airline was rebranded under the name "Capital Airlines".
- F. None of above.
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_69f76e0acfc0819082c8495c2210ce73 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_6a017114e7148190b7479284c316443d |
completed | May 11, 2026, 6:03 a.m. |
| PD | Predicate disambiguation | batch_6a016eebd60481909212e2a49ef95fbe |
completed | May 11, 2026, 5:53 a.m. |
Created at: May 3, 2026, 4:05 p.m.