Triple

T17903714
Position Surface form Disambiguated ID Type / Status
Subject Ellie Williams E447646 entity
Predicate ally P4662 FINISHED
Object Marlene
Marlene is the determined and pragmatic leader of the Fireflies resistance group in The Last of Us universe.
E1295460 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: Marlene | Statement: [Ellie Williams, ally, Marlene]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marlene
Context triple: [Ellie Williams, ally, Marlene]
  • A. Marlene
    Marlene is an energetic and friendly otter who appears as a main supporting character in the animated series "The Penguins of Madagascar."
  • B. Marlene
    Marlene is the ambitious, career-driven protagonist of Caryl Churchill’s play "Top Girls," whose life embodies the tensions between feminism, success, and personal sacrifice.
  • C. Marlene
    Marlene is a German biographical film directed by Joseph Vilsmaier about the life and career of actress and singer Marlene Dietrich.
  • D. Marlene
    Marlene is a feminine given name of German origin, often considered a blend of Maria and Magdalene and associated with figures like actress Marlene Dietrich.
  • E. Audrey
    Audrey is the sweet but beleaguered love interest and florist’s assistant in the horror-comedy musical "Little Shop of Horrors."
  • 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: Marlene
Triple: [Ellie Williams, ally, Marlene]
Generated description
Marlene is the determined and pragmatic leader of the Fireflies resistance group in The Last of Us universe.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Marlene
Target entity description: Marlene is the determined and pragmatic leader of the Fireflies resistance group in The Last of Us universe.
  • A. Marlene
    Marlene is a German biographical film directed by Joseph Vilsmaier about the life and career of actress and singer Marlene Dietrich.
  • B. Marlene
    Marlene is an energetic and friendly otter who appears as a main supporting character in the animated series "The Penguins of Madagascar."
  • C. Marlene
    Marlene is the ambitious, career-driven protagonist of Caryl Churchill’s play "Top Girls," whose life embodies the tensions between feminism, success, and personal sacrifice.
  • D. Marlene
    Marlene is a feminine given name of German origin, often considered a blend of Maria and Magdalene and associated with figures like actress Marlene Dietrich.
  • E. Audrey
    Audrey is the sweet but beleaguered love interest and florist’s assistant in the horror-comedy musical "Little Shop of Horrors."
  • 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_69d8b9f6d394819082a6d69fd1e23d2f completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e49e9a9cfc8190879fc36dfdeb562b completed April 19, 2026, 9:21 a.m.
NED1 Entity disambiguation (via context triple) batch_6a031b2a27748190b620da54b4222a37 completed May 12, 2026, 12:20 p.m.
NEDg Description generation batch_6a031c78ca108190ae678979ed85ba55 completed May 12, 2026, 12:26 p.m.
NED2 Entity disambiguation (via description) batch_6a031db7eed88190bc3d4e157be7b5fc completed May 12, 2026, 12:31 p.m.
Created at: April 10, 2026, 10:19 a.m.