Triple

T19927787
Position Surface form Disambiguated ID Type / Status
Subject Mel Jones E478971 entity
Predicate relative P37 FINISHED
Object Coraline Jones 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: Coraline Jones | Statement: [Mel Jones, relative, Coraline Jones]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Coraline Jones
Context triple: [Mel Jones, relative, Coraline Jones]
  • A. Coraline Jones chosen
    Coraline Jones is the brave and curious young heroine of Neil Gaiman’s dark fantasy novella and its film adaptation, who discovers a sinister parallel world behind a secret door in her new home.
  • B. Coralie
    Coralie is a beautiful young actress in Honoré de Balzac’s novel "Lost Illusions," known for her tragic love affair with the ambitious poet Lucien de Rubempré.
  • C. Coraline
    Coraline is a dark fantasy novella by Neil Gaiman about a young girl who discovers a sinister parallel world behind a secret door in her new home.
  • D. Lucy
    Lucy, better known by her nickname Wyldstyle, is a rebellious and resourceful Master Builder from The Lego Movie franchise.
  • E. Lucy
    Lucy is a NASA Discovery Program space mission designed to study Jupiter’s Trojan asteroids to better understand the early solar system’s formation and evolution.
  • 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_69d8e521855c8190b41871700afc8d6a completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e659cc1a448190aa98d4a66022457e completed April 20, 2026, 4:52 p.m.
Created at: April 10, 2026, 1:53 p.m.