Triple
T5299809
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | AOL–Time Warner merger |
E119946
|
entity |
| Predicate | AOLStakeInCombinedCompany |
P1553
|
FINISHED |
| Object | 55 percent |
—
|
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: 55 percent | Statement: [AOL–Time Warner merger, AOLStakeInCombinedCompany, 55 percent]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: AOLStakeInCombinedCompany Context triple: [AOL–Time Warner merger, AOLStakeInCombinedCompany, 55 percent]
-
A.
holdsStakeThrough
Indicates that one entity possesses an ownership interest in another entity indirectly, via an intermediate entity or instrument.
-
B.
memberCompany
Indicates that a company is formally part of, or affiliated as a member with, a larger organization, group, or association.
-
C.
hasStakeholder
chosen
Indicates that an entity is a stakeholder of another entity, typically having an interest, involvement, or influence in its activities or outcomes.
-
D.
acquiredCompany
Indicates that one entity has purchased and taken ownership or control of another company.
-
E.
coFounderCompany
Indicates that a person is one of the founding members who jointly established a particular company.
- 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_69bd446f22b88190b6a47fb91c68a3e7 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd8e44e7c881909b241b2fec366038 |
completed | March 20, 2026, 6:13 p.m. |
| PD | Predicate disambiguation | batch_69bd845097ac81909678624c4907fda4 |
completed | March 20, 2026, 5:30 p.m. |
Created at: March 20, 2026, 1:53 p.m.