Triple

T22293339
Position Surface form Disambiguated ID Type / Status
Subject Sapor E551053 entity
Predicate captured P4236 FINISHED
Object Valerian 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: Valerian | Statement: [Sapor, captured, Valerian]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Valerian
Context triple: [Sapor, captured, Valerian]
  • A. Valerian
    Valerian is a space-traveling special agent and the central protagonist of the science fiction film "Valerian and the City of a Thousand Planets."
  • B. Valerian chosen
    Valerian was a 3rd-century Roman emperor whose reign is most remembered for his catastrophic defeat and capture by the Sasanian king Shapur I.
  • C. Valeriana
    Valeriana is a genus of flowering plants best known for species like Valeriana officinalis, whose roots are widely used in herbal medicine as a mild sedative and sleep aid.
  • D. Angelica
    Angelica is a cunning and resourceful pirate and former love interest of Jack Sparrow who plays a central role in Pirates of the Caribbean: On Stranger Tides.
  • E. Angelica
    Angelica is a feminine given name of Latin origin, commonly associated with the meaning "angelic" or "messenger of God."
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e11e45fb848190a1b2ae21296e3a5f completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f1560de3508190951ad0806ae3cc0d completed April 29, 2026, 12:51 a.m.
Created at: April 16, 2026, 8:41 p.m.