Triple
T20320999
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pau Cristià |
E492205
|
entity |
| Predicate | roleInBarcelonaDisputation |
P60675
|
FINISHED |
| Object | Christian representative |
—
|
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: Christian representative | Statement: [Pau Cristià, roleInBarcelonaDisputation, Christian representative]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleInBarcelonaDisputation Context triple: [Pau Cristià, roleInBarcelonaDisputation, Christian representative]
-
A.
roleInDisputationOfBarcelona
chosen
Indicates that one entity held a specific role or participation status in the Disputation of Barcelona.
-
B.
conferenceDominance
Indicates that one entity holds a superior or controlling position over others within a specific conference or competitive grouping.
-
C.
authorParticipation
Indicates that an author takes part in or contributes to a specific work, project, or publication.
-
D.
conferenceCounterpart
Indicates that two entities are corresponding participants or roles in the same conference or meeting, positioned as counterparts to each other.
-
E.
roleInScholarlyCommunication
Indicates the function or position an entity holds within the processes of producing, evaluating, disseminating, or preserving scholarly work.
- 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_69e0b4a0134081909113563e1c3ba68a |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6778b8b648190b80badaf15be2599 |
completed | April 20, 2026, 6:59 p.m. |
| PD | Predicate disambiguation | batch_69e5762655ac8190a8cc48a29fa2c0c4 |
completed | April 20, 2026, 12:41 a.m. |
Created at: April 16, 2026, 11:20 a.m.