Triple
T37653988
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | UK Parliament 2005–2010 |
E937246
|
entity |
| Predicate | controllingPartyAtStart |
P57317
|
FINISHED |
| Object | Labour Party (UK) |
—
|
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: Labour Party (UK) | Statement: [UK Parliament 2005–2010, controllingPartyAtStart, Labour Party (UK)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: controllingPartyAtStart Context triple: [UK Parliament 2005–2010, controllingPartyAtStart, Labour Party (UK)]
-
A.
leadingPartyAtStart
chosen
Indicates which party was in the lead at the beginning of the specified event or time period.
-
B.
dominantParty
Indicates that one party in a relationship holds primary control, authority, or influence over the other.
-
C.
startTimeAsRulingParty
Indicates the point in time when an entity begins its tenure or role as the ruling party.
-
D.
controllingPlayer
Indicates which player currently has control or authority over a given game element, object, or situation.
-
E.
introducedParty
Indicates that one entity has brought another entity to the attention of, or formally presented them to, a third party or context.
- 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_69f76ed4fe908190b8061c5c135e0971 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69ff46afe7e481908f2862ed11c88db2 |
completed | May 9, 2026, 2:37 p.m. |
| PD | Predicate disambiguation | batch_69ff45e9151881909c444a655e852165 |
completed | May 9, 2026, 2:34 p.m. |
Created at: May 3, 2026, 4:18 p.m.