Triple
T16918858
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Recall |
E410389
|
entity |
| Predicate | hadTurnout |
P29796
|
FINISHED |
| Object | approximately 61.2% |
—
|
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: approximately 61.2% | Statement: [The Recall, hadTurnout, approximately 61.2%]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hadTurnout Context triple: [The Recall, hadTurnout, approximately 61.2%]
-
A.
turnout
chosen
Indicates the number or proportion of participants who attend or take part in an event or activity.
-
B.
hadVoteIn
Indicates that an entity participated by casting a vote in a particular decision, election, or voting event.
-
C.
hadEvent
Indicates that an entity experienced, hosted, or was associated with a specific event at some point in time.
-
D.
hadRightToElect
Indicates that an entity possessed the legal or formal authority to choose or vote for another entity in an election or selection process.
-
E.
stoodDownAtElection
Indicates that an individual chose not to stand as a candidate in a particular election in which they had previously been eligible or expected to run.
- 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_69d886c7b1e481908c3766dfa8c13458 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3cdec3d0c8190994a0fca335c65d6 |
completed | April 18, 2026, 6:31 p.m. |
| PD | Predicate disambiguation | batch_69e32b982f548190b08414d55810de19 |
completed | April 18, 2026, 6:58 a.m. |
Created at: April 10, 2026, 5:30 a.m.