Triple
T15096243
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | BATRA |
E360544
|
entity |
| Predicate | belongsToCorporateGroup |
P12263
|
FINISHED |
| Object | Liberty Media tracking stock structure |
—
|
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: Liberty Media tracking stock structure | Statement: [BATRA, belongsToCorporateGroup, Liberty Media tracking stock structure]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: belongsToCorporateGroup Context triple: [BATRA, belongsToCorporateGroup, Liberty Media tracking stock structure]
-
A.
belongsToCompany
Indicates that an entity is owned, employed, or otherwise formally associated with a specific company.
-
B.
corporateGroupType
Indicates the classification of a corporate group according to its organizational or legal type.
-
C.
belongsToGroup
chosen
Indicates that an entity is a member of, or is included within, a particular group or collection.
-
D.
belongsToCompanyType
Indicates that an entity is associated with or classified under a particular type or category of company.
-
E.
hasSubsidiaryRoleInGroup
Indicates that an entity holds a secondary or supporting role within a specified group.
- 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_69d85a035aa88190b52a139d3a1b7b6d |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e005466e9c8190a68e1fbeb8922b1a |
completed | April 15, 2026, 9:38 p.m. |
| PD | Predicate disambiguation | batch_69deb9645b9c8190a5712456dbd78029 |
completed | April 14, 2026, 10:02 p.m. |
Created at: April 10, 2026, 3:04 a.m.