Triple
T7154049
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Constitution of Andorra |
E166763
|
entity |
| Predicate | referendumYesPercentage |
P75178
|
FINISHED |
| Object | about 74% |
—
|
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: about 74% | Statement: [Constitution of Andorra, referendumYesPercentage, about 74%]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: referendumYesPercentage Context triple: [Constitution of Andorra, referendumYesPercentage, about 74%]
-
A.
referendumResult
Indicates the outcome or decision reached by voters in a specific referendum.
-
B.
referendumResultRemainPercentage
Indicates the percentage of votes in a referendum that were cast in favor of remaining (as opposed to leaving or changing the status quo).
-
C.
referendumRelated
Indicates a relationship where something is connected to, associated with, or arising from a referendum process or its outcomes.
-
D.
referendumResultLeavePercentage
Indicates the percentage of votes in a referendum that were cast in favor of the "leave" option.
-
E.
referendumDate
Indicates the specific date on which a referendum is scheduled to or did take place.
- F. None of above. chosen
Provenance (4 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_69c68886779c8190a8e3fbabffe68253 |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6e7f68384819095e6aef89555442a |
completed | March 27, 2026, 8:26 p.m. |
| PD | Predicate disambiguation | batch_69c6e1caf4e48190b47bb398a3c1554d |
completed | March 27, 2026, 8 p.m. |
| PDg | Predicate description generation | batch_69c6e4a213508190a40aca39f9eee7d5 |
completed | March 27, 2026, 8:12 p.m. |
Created at: March 27, 2026, 2:46 p.m.