Triple
T37643205
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jeepney TV |
E936666
|
entity |
| Predicate | programLibrarySource |
P189770
|
FINISHED |
| Object | ABS-CBN archives |
—
|
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: ABS-CBN archives | Statement: [Jeepney TV, programLibrarySource, ABS-CBN archives]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: programLibrarySource Context triple: [Jeepney TV, programLibrarySource, ABS-CBN archives]
-
A.
gameLibrarySource
Indicates the origin or provider from which a game was obtained or added to a game library.
-
B.
softwareLibrary
Indicates that one entity is a software library that provides code, functionality, or services used by another entity.
-
C.
programIncluded
Indicates that a particular program is contained within, or forms part of, another specified collection, package, or set of programs.
-
D.
programmaticSource
Indicates that something originates from, is generated by, or is derived through a programmatic or automated process rather than manual creation.
-
E.
softwareLibraryCreated
Indicates that an entity (typically a person or organization) is responsible for creating a particular software library.
- F. None of above. chosen
Provenance (4 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_69fbca6c066c8190a1599202f341417f |
completed | May 6, 2026, 11:10 p.m. |
| PD | Predicate disambiguation | batch_69fbc8ec03ac8190a757563f96fab283 |
completed | May 6, 2026, 11:04 p.m. |
| PDg | Predicate description generation | batch_69fbc9d0854c8190aa00093274afebb8 |
completed | May 6, 2026, 11:08 p.m. |
Created at: May 3, 2026, 4:18 p.m.