Triple

T11992648
Position Surface form Disambiguated ID Type / Status
Subject Sara Crewe E285445 entity
Predicate hasDoll P92902 FINISHED
Object Emily E315868 NE FINISHED

How this triple was built (3 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: Emily | Statement: [Sara Crewe, hasDoll, Emily]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Emily
Context triple: [Sara Crewe, hasDoll, Emily]
  • A. Emily
    Emily Warren Roebling was a pioneering 19th-century American engineer best known for her crucial role in overseeing the completion of the Brooklyn Bridge.
  • B. Emily
    Emily is the NATO reporting name for the Kawanishi H8K, a World War II-era Japanese four-engine flying boat used primarily for long-range maritime patrol and reconnaissance.
  • C. Emily chosen
    Emily is a given name commonly used in English-speaking countries, often associated with literary, historical, and contemporary cultural figures.
  • D. Emily
    "Emily" is a 2022 British biographical drama film about the life of writer Emily Brontë, starring Fionn Whitehead alongside Emma Mackey.
  • E. Emma
    "Emma" is a 2009 British television miniseries adaptation of Jane Austen's novel, starring Romola Garai in the title role.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasDoll
Context triple: [Sara Crewe, hasDoll, Emily]
  • A. hasDroidCharacter
    Indicates that an entity features or includes a character that is a droid.
  • B. hasLie
    Indicates that an entity is associated with or responsible for a specific lie or false statement.
  • C. hasPuppetCharacter chosen
    Indicates that one entity features, includes, or is associated with a particular puppet character as part of its content or composition.
  • D. hasDial
    Indicates that an object is equipped with or features a dial control as part of its interface or mechanism.
  • E. hasGadget
    Indicates that an entity possesses, uses, or is equipped with a particular gadget.
  • F. None of above.

Provenance (4 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_69d6ab44a77c8190a652f4b27164e4ef completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d903b11ac481909866b611380792e7 completed April 10, 2026, 2:05 p.m.
NED1 Entity disambiguation (via context triple) batch_69f48abcf2588190a44e6e31e045b356 completed May 1, 2026, 11:13 a.m.
PD Predicate disambiguation batch_69d902abca70819098291aa51b593708 completed April 10, 2026, 2:01 p.m.
Created at: April 8, 2026, 9:46 p.m.