Triple
T31729004
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Grail Knights |
E809803
|
entity |
| Predicate | conflictInWork |
P1406
|
FINISHED |
| Object | crisis caused by Amfortas’s wound |
—
|
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: crisis caused by Amfortas’s wound | Statement: [The Grail Knights, conflictInWork, crisis caused by Amfortas’s wound]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: conflictInWork Context triple: [The Grail Knights, conflictInWork, crisis caused by Amfortas’s wound]
-
A.
conflictIn
chosen
Indicates that one entity is involved in, associated with, or occurs within a particular conflict or dispute.
-
B.
conflictActivity
Indicates that an entity is engaged in, associated with, or affected by a conflict-related action or event.
-
C.
conflictedBetween
Indicates being torn or uncertain between two or more options, positions, or commitments.
-
D.
internalConflict
Indicates a relationship where an entity experiences opposing desires, beliefs, or motives within itself, leading to psychological or emotional tension.
-
E.
subjectConflict
Indicates that there is a disagreement, clash, or opposing stance between the subject and another party or situation.
- 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_69f348e009c8819095d77df52c645b9c |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6e6029a10819098ff21f58079e70e |
completed | May 3, 2026, 6:06 a.m. |
| PD | Predicate disambiguation | batch_69f6e3d5e8188190b1e1c2e5d1b77031 |
completed | May 3, 2026, 5:57 a.m. |
Created at: April 30, 2026, 11:21 p.m.