Triple
T11454200
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Phalaris |
E271481
|
entity |
| Predicate | associatedWithTortureMethod |
P13133
|
FINISHED |
| Object | roasting victims in a metal bull |
—
|
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: roasting victims in a metal bull | Statement: [Phalaris, associatedWithTortureMethod, roasting victims in a metal bull]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedWithTortureMethod Context triple: [Phalaris, associatedWithTortureMethod, roasting victims in a metal bull]
-
A.
useOfTorture
Indicates the intentional infliction or use of torture by one entity upon another, typically to punish, coerce, intimidate, or extract information.
-
B.
methodOfPersecution
chosen
Indicates the specific means, technique, or process by which an act of persecution is carried out.
-
C.
torturedAt
Indicates that an entity was subjected to torture at a specific location or facility.
-
D.
usedMethodOfKilling
Indicates that one entity employed a particular method or means to carry out a killing of another entity.
-
E.
numberOfTortureVictims
Indicates the quantity of individuals who have been subjected to torture.
- 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_69d6aadff8888190a13f253f0d460874 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d822f2138081909408c7916cef99c9 |
completed | April 9, 2026, 10:06 p.m. |
| PD | Predicate disambiguation | batch_69d80867ff248190bb157fa9e355353b |
completed | April 9, 2026, 8:13 p.m. |
Created at: April 8, 2026, 9:35 p.m.