Triple
T10363146
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2014 Catalan self-determination referendum |
E244184
|
entity |
| Predicate | ballotFormat |
P30499
|
FINISHED |
| Object | yes-yes / yes-no / no options |
—
|
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: yes-yes / yes-no / no options | Statement: [2014 Catalan self-determination referendum, ballotFormat, yes-yes / yes-no / no options]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ballotFormat Context triple: [2014 Catalan self-determination referendum, ballotFormat, yes-yes / yes-no / no options]
-
A.
ballotStructure
chosen
Indicates how options, candidates, or choices are organized and presented on a ballot for selection.
-
B.
ballot
Indicates that an entity participates in a formal voting process, typically by casting or submitting a vote or choice.
-
C.
ballotPreparationBy
Indicates that one entity is responsible for preparing or organizing the ballot used by another entity in an election or voting process.
-
D.
ballotSize
Indicates the number of distinct options or items presented on a given ballot in an election or voting process.
-
E.
ballotStatus
Indicates the current state or outcome of a ballot within a voting or decision-making process.
- 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_69d381b3e328819094b23b8edcd29b5a |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4e963a6148190822951e72590b9df |
completed | April 7, 2026, 11:24 a.m. |
| PD | Predicate disambiguation | batch_69d4dfa657f481909cc5cc8fec00ad19 |
completed | April 7, 2026, 10:42 a.m. |
Created at: April 6, 2026, noon