Triple
T23354570
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Plenary of the Congress of Deputies |
E593008
|
entity |
| Predicate | debateFormat |
P115494
|
FINISHED |
| Object | plenary debates |
—
|
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: plenary debates | Statement: [Plenary of the Congress of Deputies, debateFormat, plenary debates]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: debateFormat Context triple: [Plenary of the Congress of Deputies, debateFormat, plenary debates]
-
A.
hasDebateFormat
chosen
Indicates that a particular debate, event, or context uses or follows a specified debate format or structure.
-
B.
settingOfDebate
Indicates the context, environment, or circumstances in which a particular debate takes place.
-
C.
debateOrganizer
Indicates that one entity is responsible for organizing, coordinating, or managing a debate involving another entity or entities.
-
D.
debateModerator
Indicates that one entity serves as the moderator overseeing and managing a debate involving another entity or entities.
-
E.
canDebate
Indicates that one entity has the ability or permission to engage in a debate or argumentative discussion with another entity.
- 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_69e25d24d2a4819092e6ede74c2a918d |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f19a169bb88190a2ca659fce1133e5 |
completed | April 29, 2026, 5:41 a.m. |
| PD | Predicate disambiguation | batch_69effcfd8d288190937a887fe6023c11 |
completed | April 28, 2026, 12:19 a.m. |
Created at: April 17, 2026, 5:20 p.m.