Triple
T31904778
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Theresa May confidence vote (December 2018) |
E814517
|
entity |
| Predicate | triggerThreshold |
P14326
|
FINISHED |
| Object | 48 Conservative MPs |
—
|
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: 48 Conservative MPs | Statement: [Theresa May confidence vote (December 2018), triggerThreshold, 48 Conservative MPs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: triggerThreshold Context triple: [Theresa May confidence vote (December 2018), triggerThreshold, 48 Conservative MPs]
-
A.
thresholdMet
Indicates that a specified limit or condition has been reached or exceeded.
-
B.
thresholdFor
chosen
Indicates that one entity specifies the minimum or limiting value at which a condition, effect, or state involving another entity begins to occur or change.
-
C.
triggerCondition
Indicates the specific circumstances or state under which an associated event, action, or process is initiated or activated.
-
D.
trigger
Indicates that one entity causes or initiates an event, state, or action in another entity or system.
-
E.
trapTrigger
Indicates that an entity activates or sets off a trap in the environment.
- 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_69f348f04d7881909537fc9e7cbc670e |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6b1b2be408190bef7834aa16578a8 |
completed | May 3, 2026, 2:23 a.m. |
| PD | Predicate disambiguation | batch_69f6aca59d4881908d14ed47962703bd |
completed | May 3, 2026, 2:02 a.m. |
Created at: May 1, 2026, midnight