Triple
T14613449
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | COA |
E343016
|
entity |
| Predicate | historicalAssociationEndReason |
P71729
|
FINISHED |
| Object | merger with United Airlines |
—
|
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: merger with United Airlines | Statement: [COA, historicalAssociationEndReason, merger with United Airlines]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: historicalAssociationEndReason Context triple: [COA, historicalAssociationEndReason, merger with United Airlines]
-
A.
reasonForAssociation
Indicates that one entity is associated with another due to a specific cause, purpose, or motivating factor underlying their relationship.
-
B.
affiliationEndedWith
chosen
Indicates that a previously existing affiliation or association between entities has come to an end at a specific point in time or under certain conditions.
-
C.
dateOfHistoricalAssociation
Indicates the specific date or time period during which a notable historical association, connection, or event between entities took place.
-
D.
originallyAssociatedWith
Indicates that an entity was first linked, connected, or affiliated with another entity before any later changes in association.
-
E.
historicallyGroupedWith
Indicates that two or more entities have been associated or classified together in the past based on historical context, usage, or tradition, even if they are no longer grouped that way.
- 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_69d822dec68081908c2553145c4051dc |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb45264988190a1df13e8b54a85bd |
completed | April 14, 2026, 9:40 p.m. |
| PD | Predicate disambiguation | batch_69de656f9f4c81909f815b6629a9ee39 |
completed | April 14, 2026, 4:03 p.m. |
Created at: April 10, 2026, 1:25 a.m.