Triple

T13054701
Position Surface form Disambiguated ID Type / Status
Subject Hannah John-Kamen E327539 entity
Predicate characterPortrayed P1507 FINISHED
Object Ghost E327543 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: Ghost | Statement: [Hannah John-Kamen, characterPortrayed, Ghost]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ghost
Context triple: [Hannah John-Kamen, characterPortrayed, Ghost]
  • A. Ghost
    "Ghost" is a song by the English rock band The Police, featured on their 1981 album "Ghost in the Machine."
  • B. Ghost
    "Ghost" is a supernatural-themed television series that follows the eerie and often emotional encounters between the living and lingering spirits.
  • C. Ghost
    Ghost is a mysterious and highly skilled special forces operative from the Call of Duty: Modern Warfare series, recognizable by his skull-patterned balaclava and covert operations role.
  • D. Ghost
    "Ghost" is an electropop song by American singer Halsey that served as her breakout debut single and introduced her dark, confessional style.
  • E. Ghost chosen
    Ghost is a Marvel Comics supervillain-turned-antihero known for their high-tech suit that grants intangibility and invisibility, appearing as a key adversary in the film "Ant-Man and the Wasp."
  • 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_69d8076e64308190904fb5c93517c901 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69d980bb52d88190b5be12000e27a2c9 completed April 10, 2026, 10:59 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6f5c771fc8190afb6b0f449c67294 completed May 3, 2026, 7:14 a.m.
Created at: April 9, 2026, 8:58 p.m.