Triple
T2394587
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Apollinarianism |
E47618
|
entity |
| Predicate | condemnationDate |
P5487
|
FINISHED |
| Object | 381 |
—
|
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: 381 | Statement: [Apollinarianism, condemnationDate, 381]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: condemnationDate Context triple: [Apollinarianism, condemnationDate, 381]
-
A.
condemnedInYear
chosen
Indicates that an entity was formally condemned or denounced in a specific calendar year.
-
B.
condemnation
Indicates that an entity expresses strong disapproval or denunciation of another entity, action, or situation.
-
C.
dateDestroyed
Indicates the specific date on which an entity was destroyed or ceased to exist.
-
D.
retrocessionDate
Indicates the date on which rights, obligations, or control previously transferred are formally returned or reassigned back to the original party or another designated party.
-
E.
condemnedAs
Indicates that one entity formally or strongly denounces another entity by labeling it as wrong, guilty, or unacceptable.
- 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_69a88a1c450c81909f61abb8b6863885 |
completed | March 4, 2026, 7:38 p.m. |
| NER | Named-entity recognition | batch_69abc87827d88190bb2351a688e6de32 |
completed | March 7, 2026, 6:40 a.m. |
| PD | Predicate disambiguation | batch_69abc5a3825c81909ec6111dfc165453 |
completed | March 7, 2026, 6:28 a.m. |
Created at: March 4, 2026, 7:57 p.m.