Triple
T7462443
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Companion Pass |
E176283
|
entity |
| Predicate | qualificationSource |
P71390
|
FINISHED |
| Object | Southwest revenue flights |
—
|
LITERAL 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: Southwest revenue flights | Statement: [Companion Pass, qualificationSource, Southwest revenue flights]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: qualificationSource Context triple: [Companion Pass, qualificationSource, Southwest revenue flights]
-
A.
qualificationProcess
Indicates the process or set of steps through which an entity is evaluated and approved as meeting required qualifications or standards.
-
B.
commissioningSource
Indicates the origin or authority (such as an institution, program, or body) that formally granted someone their commission or official appointment.
-
C.
providedQualificationFor
chosen
Indicates that one entity supplied or granted a qualification, credential, or certification that another entity possesses or uses.
-
D.
personnelSource
Indicates the origin or provider from which personnel are obtained or assigned.
-
E.
reputationInSources
Indicates that an entity has a certain reputation or standing as reflected or reported in various information sources.
- 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_69c69f21632481908bf83f6c6da897e3 |
completed | March 27, 2026, 3:15 p.m. |
| NER | Named-entity recognition | batch_69c6f3d80ae08190ba383066cf0cb2ce |
completed | March 27, 2026, 9:17 p.m. |
| PD | Predicate disambiguation | batch_69c6f03bad9c8190bdd5abb86d37df47 |
completed | March 27, 2026, 9:01 p.m. |
Created at: March 27, 2026, 3:39 p.m.