Triple

T24064065
Position Surface form Disambiguated ID Type / Status
Subject United States Marine Corps barracks (Beirut) E596037 entity
Predicate perpetratorAttributedTo P698 FINISHED
Object Hezbollah NE NERFINISHED

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: Hezbollah | Statement: [United States Marine Corps barracks (Beirut), perpetratorAttributedTo, Hezbollah]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: perpetratorAttributedTo
Context triple: [United States Marine Corps barracks (Beirut), perpetratorAttributedTo, Hezbollah]
  • A. perpetratedBy chosen
    Indicates that an action, event, or wrongdoing was carried out or caused by a particular agent or entity.
  • B. perpetratorAlias
    Indicates that an entity is known or referred to by an alternative name or alias specifically in the context of being the perpetrator of an act or offense.
  • C. perpetratorType
    Indicates the classification or category of the entity that carried out or is responsible for a harmful, illegal, or otherwise wrongful act.
  • D. perpetratorClaimedBy
    Indicates that a person or entity is identified or asserted as the perpetrator of an act, event, or offense by another party.
  • E. perpetratorNationality
    Indicates the country or nationality to which a perpetrator of an act, crime, or harmful event belongs.
  • 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_69e288c25c008190850cf447940ab181 completed April 17, 2026, 7:23 p.m.
NER Named-entity recognition batch_69f1da598dec8190a625309fd8f10f1d completed April 29, 2026, 10:15 a.m.
PD Predicate disambiguation batch_69f1764b1d4c8190b12590c6339c31c1 completed April 29, 2026, 3:08 a.m.
Created at: April 17, 2026, 10:39 p.m.