Triple
T24633790
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ITV North of England |
E609749
|
entity |
| Predicate | mainFranchiseCompany |
P52447
|
FINISHED |
| Object | Granada Television |
—
|
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: Granada Television | Statement: [ITV North of England, mainFranchiseCompany, Granada Television]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mainFranchiseCompany Context triple: [ITV North of England, mainFranchiseCompany, Granada Television]
-
A.
franchiseParentCompany
chosen
Indicates that one company is the overarching parent organization that owns or controls a franchise operated by another entity.
-
B.
franchiseOf
Indicates that one entity operates as a franchise belonging to or licensed by another entity.
-
C.
franchiseName
Indicates that an entity is identified by or associated with a specific franchise’s official name.
-
D.
franchiseBrand
Indicates that one entity is the brand under which another entity operates as a franchise.
-
E.
franchiseConnection
Indicates a relationship where one entity is part of, derived from, or otherwise officially linked to a larger franchise or brand.
- 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_69e2c4d28f848190ac38c400060e943d |
completed | April 17, 2026, 11:40 p.m. |
| NER | Named-entity recognition | batch_69f2be064ff88190b5d9e5ec75a41242 |
completed | April 30, 2026, 2:27 a.m. |
| PD | Predicate disambiguation | batch_69f2a6d0ab708190b2e3b94dd20ca76b |
completed | April 30, 2026, 12:48 a.m. |
Created at: April 18, 2026, 2:32 a.m.