Triple
T7785696
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Barnabas |
E187237
|
entity |
| Predicate | conflictReason |
P6503
|
FINISHED |
| Object | disagreement over John Mark |
—
|
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: disagreement over John Mark | Statement: [Barnabas, conflictReason, disagreement over John Mark]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: conflictReason Context triple: [Barnabas, conflictReason, disagreement over John Mark]
-
A.
reasonForConflict
chosen
Indicates that one entity is the cause, motive, or underlying issue leading to a conflict involving another entity.
-
B.
reportedConflict
Indicates that one party has formally reported the existence of a conflict involving another party or situation.
-
C.
conflictIn
Indicates that one entity is involved in, associated with, or occurs within a particular conflict or dispute.
-
D.
conflictResolvedBy
Indicates that a conflict or dispute is settled or addressed through the actions, decisions, or intervention of a specified entity or process.
-
E.
conflictedBetween
Indicates being torn or uncertain between two or more options, positions, or commitments.
- 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_69ca82af2d2c8190963861f5e0b8bf21 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cae7e779ec8190b77296d9c2ac3210 |
completed | March 30, 2026, 9:15 p.m. |
| PD | Predicate disambiguation | batch_69caa488532c819093ac40bba0b3c7ef |
completed | March 30, 2026, 4:27 p.m. |
Created at: March 30, 2026, 4:23 p.m.