Triple
T37643204
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jeepney TV |
E936666
|
entity |
| Predicate | contentRightsHolder |
P1365
|
FINISHED |
| Object | ABS-CBN Corporation |
—
|
NE NERFINISHED |
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: ABS-CBN Corporation | Statement: [Jeepney TV, contentRightsHolder, ABS-CBN Corporation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: contentRightsHolder Context triple: [Jeepney TV, contentRightsHolder, ABS-CBN Corporation]
-
A.
commercialRightsHolderOf
Indicates that one entity holds the legal commercial rights to exploit, license, or profit from another entity.
-
B.
copyrightHolderUniverse
Indicates that one entity is the legal copyright holder for works within a specified universe or fictional setting.
-
C.
laterRightsHolderOfWork
Indicates that the subject is a subsequent rights holder who acquired the rights to the work after an earlier rights holder.
-
D.
hasCopyrightHolder
chosen
Indicates that a specified entity holds the legal copyright ownership or rights over another entity.
-
E.
rightsHolderOfOriginalWork
Indicates that an entity holds the legal rights to the original version of a work from which derivatives or copies may be made.
- 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_69f76ed31d8881908405da6c6d2f0463 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fd05ba6b2c81909c62b46237d10365 |
completed | May 7, 2026, 9:35 p.m. |
| PD | Predicate disambiguation | batch_69fd03039e48819082b6e12c5453885a |
completed | May 7, 2026, 9:24 p.m. |
Created at: May 3, 2026, 4:18 p.m.