Triple

T18008730
Position Surface form Disambiguated ID Type / Status
Subject Kazu Kibuishi E430820 entity
Predicate hasSeries P1761 FINISHED
Object Amulet 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: Amulet | Statement: [Kazu Kibuishi, hasSeries, Amulet]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Amulet
Context triple: [Kazu Kibuishi, hasSeries, Amulet]
  • A. Amulet
    Amulet is a 2020 British psychological horror film directed by and starring Romola Garai, known for its unsettling atmosphere and feminist themes.
  • B. Amulet
    "Amulet" is a song by Paul Simon from his 2011 album *So Beautiful or So What*, noted for its reflective, folk-influenced sound and lyrical depth.
  • C. Amulet
    Amulet is a short novel by Chilean author Roberto Bolaño that follows the haunting, stream-of-consciousness monologue of a woman trapped in a university bathroom during the 1968 Mexican army massacre at Tlatelolco.
  • D. Amulet
    Amulet is a notable work by the Dutch poet and visual artist Lucebert, reflecting his influential role in postwar experimental literature and art.
  • E. Amulet chosen
    Amulet is a popular all-ages fantasy graphic novel series by Kazu Kibuishi that follows siblings who discover a powerful magical amulet and a hidden world filled with danger and adventure.
  • 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_69d8b904530081908bf341d842464856 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4b51e13788190bebbbdd7340e0982 completed April 19, 2026, 10:57 a.m.
Created at: April 10, 2026, 10:24 a.m.