Triple
T5420498
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bohemond II of Antioch |
E121235
|
entity |
| Predicate | bodyTreatmentAfterDeath |
P57847
|
FINISHED |
| Object | decapitation |
—
|
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: decapitation | Statement: [Bohemond II of Antioch, bodyTreatmentAfterDeath, decapitation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bodyTreatmentAfterDeath Context triple: [Bohemond II of Antioch, bodyTreatmentAfterDeath, decapitation]
-
A.
bodyLocationAfterDeath
Indicates the location or position of an entity’s body after its death.
-
B.
bodyMistreatedAfterDeathBy
chosen
Indicates that a person's body was subjected to mistreatment or abuse after their death by another agent.
-
C.
deathDescribedAs
Indicates that one entity characterizes, portrays, or refers to another entity’s death using a particular description, metaphor, or wording.
-
D.
deathOutcome
Indicates that an event, condition, or action results in the death of the affected entity.
-
E.
deathDescribedIn
Indicates that a person's death is documented, narrated, or otherwise detailed within a particular source or description.
- 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_69bd463b58d88190b258261573de9e91 |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd87e8f1cc81908b997f8a417697c0 |
completed | March 20, 2026, 5:46 p.m. |
| PD | Predicate disambiguation | batch_69bd8469f5e48190bbe5c8bdfe8925ea |
completed | March 20, 2026, 5:31 p.m. |
Created at: March 20, 2026, 2:06 p.m.