Triple

T21443477
Position Surface form Disambiguated ID Type / Status
Subject Mardi: And a Voyage Thither E529002 entity
Predicate hasCharacter P2308 FINISHED
Object Taji 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: Taji | Statement: [Mardi: And a Voyage Thither, hasCharacter, Taji]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Taji
Context triple: [Mardi: And a Voyage Thither, hasCharacter, Taji]
  • A. Taji chosen
    Taji is a central character in Herman Melville’s philosophical romance "Mardi," serving as the narrator and guide through its allegorical island world.
  • B. Taji
    Taji is a town in central Iraq, located just north of Baghdad and known for its large military base and strategic importance.
  • C. Al-Ouja
    Al-Ouja is a village near Tikrit in Iraq, best known as the birthplace of former Iraqi president Saddam Hussein.
  • D. Tanta
    Tanta is a major city in northern Egypt that serves as an important commercial and transportation hub in the Nile Delta.
  • E. Tanta
    Tanta is a small Andean town in Peru known for its high-altitude landscapes and traditional rural life within the Nor Yauyos-Cochas scenic reserve.
  • 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_69e0c4569fa081908101baa24f8745db completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69e8b7055d148190ae3b52e10abd8fd2 completed April 22, 2026, 11:54 a.m.
Created at: April 16, 2026, 6:05 p.m.