Triple

T15725050
Position Surface form Disambiguated ID Type / Status
Subject Jotapata E381198 entity
Predicate capturedBy P4712 FINISHED
Object Vespasian E12684 NE 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: Vespasian | Statement: [Jotapata, capturedBy, Vespasian]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Vespasian
Context triple: [Jotapata, capturedBy, Vespasian]
  • A. Vespasian chosen
    Vespasian was a 1st-century Roman emperor best known for restoring stability after Nero’s reign and initiating major building projects such as the Colosseum.
  • B. Emperor Titus
    Emperor Titus was a 1st-century Roman emperor of the Flavian dynasty, best known for completing the Colosseum and for his military victories, including the siege of Jerusalem.
  • C. Claudi
    Claudi is a given name, typically a variant or shortened form of names like Claudiu or Claudia used in various European languages.
  • D. Tiberius
    Tiberius was a Byzantine emperor associated with the ruling House of Heraclius during the early medieval period.
  • E. Tiberius
    Tiberius was the second Roman emperor, ruling from AD 14 to 37, known for his capable early administration and later reclusive, often harsh governance.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69d86d9cdb648190bf3171be0bd7d872 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e04fb357a88190a92641c8a8c20573 completed April 16, 2026, 2:55 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff9981e0d081909617b5d686905d3a completed May 9, 2026, 8:30 p.m.
Created at: April 10, 2026, 4:46 a.m.