Triple

T15551027
Position Surface form Disambiguated ID Type / Status
Subject Jaqen H'ghar E370743 entity
Predicate occupation P3 FINISHED
Object Faceless Man E1014114 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: Faceless Man | Statement: [Jaqen H'ghar, occupation, Faceless Man]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Faceless Man
Context triple: [Jaqen H'ghar, occupation, Faceless Man]
  • A. Faceless Men chosen
    The Faceless Men are a secretive guild of mystical assassins from the House of Black and White in Braavos, known for their ability to change faces and identities at will.
  • B. Shadow Man
    "Shadow Man" is a song by Brazilian singer-songwriter Telefone, likely blending introspective lyrics with atmospheric, genre-bending production.
  • C. Ugly Man
    Ugly Man is a collection of dark, experimental short stories by American writer Dennis Cooper, known for its transgressive themes and minimalist style.
  • D. Mirror Man
    "Mirror Man" is a synth-pop song by British band The Human League, released in 1982 and known for its Motown-inspired sound and chart success.
  • E. Mirror Man
    Mirror Man is a skilled and fast-talking accomplice in the heist crew led by car thief Memphis Raines in the film "Gone in 60 Seconds."
  • 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_69d85cc6cf40819091f4a5facee1ebe6 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04a9551288190a583e8291c35f521 completed April 16, 2026, 2:33 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff4c3e67c881909a9fa1e483a364be completed May 9, 2026, 3:01 p.m.
Created at: April 10, 2026, 4:08 a.m.