Triple

T9937015
Position Surface form Disambiguated ID Type / Status
Subject Maleficent E193983 entity
Predicate featuresCharacter P626 FINISHED
Object Diaval
Diaval is the loyal raven who serves as Maleficent’s shapeshifting companion and confidant in Disney’s "Maleficent" films.
E831345 NE FINISHED

How this triple was built (4 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: Diaval | Statement: [Maleficent, featuresCharacter, Diaval]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Diaval
Context triple: [Maleficent, featuresCharacter, Diaval]
  • A. Tarasque
    The Tarasque is a legendary dragon-like monster from Provençal folklore, famously tamed by Saint Martha and associated with the town of Tarascon in southern France.
  • B. Rodach
    The Rodach is a river in Germany that flows through northern Bavaria and Thuringia before joining the Main River.
  • C. Crowle
    Crowle is a small market town and civil parish situated on the Isle of Axholme in North Lincolnshire, England.
  • D. Basilisk
    The Basilisk is a gigantic, deadly serpent from the Harry Potter series whose gaze can kill and whose venom is among the most lethal magical substances.
  • E. Dorohusk
    Dorohusk is a village in eastern Poland near the Ukrainian border, known as an important road and rail border crossing point between the two countries.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Diaval
Triple: [Maleficent, featuresCharacter, Diaval]
Generated description
Diaval is the loyal raven who serves as Maleficent’s shapeshifting companion and confidant in Disney’s "Maleficent" films.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Diaval
Target entity description: Diaval is the loyal raven who serves as Maleficent’s shapeshifting companion and confidant in Disney’s "Maleficent" films.
  • A. Tarasque
    The Tarasque is a legendary dragon-like monster from Provençal folklore, famously tamed by Saint Martha and associated with the town of Tarascon in southern France.
  • B. Rodach
    The Rodach is a river in Germany that flows through northern Bavaria and Thuringia before joining the Main River.
  • C. Crowle
    Crowle is a small market town and civil parish situated on the Isle of Axholme in North Lincolnshire, England.
  • D. Basilisk
    The Basilisk is a gigantic, deadly serpent from the Harry Potter series whose gaze can kill and whose venom is among the most lethal magical substances.
  • E. Dorohusk
    Dorohusk is a village in eastern Poland near the Ukrainian border, known as an important road and rail border crossing point between the two countries.
  • F. None of above. chosen

Provenance (5 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_69ca82e409348190a393777356b80a2a completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cdb5e4e19881909879b394090d6629 completed April 2, 2026, 12:18 a.m.
NED1 Entity disambiguation (via context triple) batch_69d228e7247c81908dbba76199f2e93f completed April 5, 2026, 9:18 a.m.
NEDg Description generation batch_69d22a2831348190909b9507edfe49f3 completed April 5, 2026, 9:23 a.m.
NED2 Entity disambiguation (via description) batch_69d22af8914c8190a8116a37a42b633c completed April 5, 2026, 9:27 a.m.
Created at: March 30, 2026, 8:44 p.m.