Triple
T20981615
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Amycus |
E516776
|
entity |
| Predicate | treatmentOfDefeatedOpponents |
P66306
|
FINISHED |
| Object | killed them |
—
|
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: killed them | Statement: [Amycus, treatmentOfDefeatedOpponents, killed them]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: treatmentOfDefeatedOpponents Context triple: [Amycus, treatmentOfDefeatedOpponents, killed them]
-
A.
treatmentAfterDefeat
Indicates that one entity’s treatment of another occurs subsequent to that other entity’s defeat.
-
B.
defeatedBy
Indicates that one entity has been beaten, overcome, or conquered by another in a contest, conflict, or competition.
-
C.
afterDefeat
Indicates that one event, state, or action occurs subsequent to and as a consequence of a defeat of some party or entity.
-
D.
consequenceForOpponents
chosen
Indicates that one party’s actions or status result in negative outcomes, penalties, or repercussions specifically for their opponents.
-
E.
wasBeaten
Indicates that one entity defeated or physically overpowered another in a contest, conflict, or confrontation.
- 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_69e0b4ffac148190bbade9f0eceb660b |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6fbdea4988190bd091a5434acc376 |
completed | April 21, 2026, 4:23 a.m. |
| PD | Predicate disambiguation | batch_69e5dbe6976081908abd4e9c8734bae9 |
completed | April 20, 2026, 7:55 a.m. |
Created at: April 16, 2026, 1:48 p.m.