Triple
T218252
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Glazer family |
E4155
|
entity |
| Predicate | ownershipTypeOfManchesterUnited |
P7585
|
FINISHED |
| Object | leveraged buyout |
—
|
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: leveraged buyout | Statement: [Glazer family, ownershipTypeOfManchesterUnited, leveraged buyout]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ownershipTypeOfManchesterUnited Context triple: [Glazer family, ownershipTypeOfManchesterUnited, leveraged buyout]
-
A.
ownershipType
chosen
Indicates the specific nature or category of the ownership relationship that one entity holds over another.
-
B.
ownershipStructure
Indicates how ownership or control is distributed among entities within an organization or asset.
-
C.
ownedBy
Indicates that one entity possesses legal or rightful ownership of another entity.
-
D.
ownsMajorFranchiseIn
Indicates that an entity has controlling or primary ownership of a major franchise operating within a specified location or jurisdiction.
-
E.
memberOfSportsTeamOwned
Indicates that an entity is a member of a sports team that is owned by another specified entity.
- 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_69a2573508588190b522c2476d91acfe |
completed | Feb. 28, 2026, 2:47 a.m. |
| NER | Named-entity recognition | batch_69a25c5199d8819096736c11077adec3 |
completed | Feb. 28, 2026, 3:09 a.m. |
| PD | Predicate disambiguation | batch_69a25b5357bc8190b29a48e3053fb76d |
completed | Feb. 28, 2026, 3:04 a.m. |
Created at: Feb. 28, 2026, 2:53 a.m.