Triple

T7472073
Position Surface form Disambiguated ID Type / Status
Subject Marlene E176530 entity
Predicate hasTitle P38 FINISHED
Object Marlene E176530 NE FINISHED

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: Marlene | Statement: [Marlene, hasTitle, Marlene]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marlene
Context triple: [Marlene, hasTitle, Marlene]
  • A. Marlene chosen
    Marlene is a German biographical film directed by Joseph Vilsmaier about the life and career of actress and singer Marlene Dietrich.
  • B. Audrey
    Audrey is a simple, rustic shepherdess who serves as a comic character in William Shakespeare’s pastoral comedy "As You Like It."
  • C. Audrey
    Audrey is a kind-hearted, nature-loving girl in the 2012 animated film "The Lorax" whose dream of seeing real trees inspires the protagonist’s quest.
  • D. Audrey
    Audrey is a feminine given name of Old English origin, traditionally meaning "noble strength" and borne by numerous notable figures in politics, arts, and entertainment.
  • E. Gloria
    "Gloria" is a 2023 studio album by English singer-songwriter Sam Smith that explores themes of self-acceptance, love, and queer identity through pop and soul-influenced tracks.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69c69f223fd88190b4c69b95d7cbeeda completed March 27, 2026, 3:15 p.m.
NER Named-entity recognition batch_69c6f415b5cc81909e1e097c90f460b6 completed March 27, 2026, 9:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69c83480a40c8190a7ae3e08022735a1 completed March 28, 2026, 8:05 p.m.
Created at: March 27, 2026, 3:41 p.m.