Triple
T21462799
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thames Television |
E529513
|
entity |
| Predicate | lostITVFranchiseIn |
P15133
|
FINISHED |
| Object | 1991 |
—
|
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: 1991 | Statement: [Thames Television, lostITVFranchiseIn, 1991]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lostITVFranchiseIn Context triple: [Thames Television, lostITVFranchiseIn, 1991]
-
A.
losingFranchise
chosen
Indicates that one entity ceases to hold or control a franchise previously granted to it by another entity.
-
B.
loserFranchise
Indicates a relationship where a sports franchise is characterized as consistently unsuccessful or underperforming, often failing to achieve significant wins or championships.
-
C.
originalITVFranchise
Indicates that an entity was the initial holder of a specific ITV broadcasting franchise for a given region or service.
-
D.
franchiseOfLosingTeam
Indicates that one entity is the franchise to which the losing team in a given game or competition belongs.
-
E.
lostDuring
Indicates that something ceased to be in possession or was no longer retained while a particular event, process, or time period was occurring.
- 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_69e0c458133481908ae8b41a12c4edec |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9e9efdb188190be79b72e1bd18860 |
completed | April 23, 2026, 9:44 a.m. |
| PD | Predicate disambiguation | batch_69e631df1b38819088d3604854e697b4 |
completed | April 20, 2026, 2:02 p.m. |
Created at: April 16, 2026, 6:09 p.m.