Triple

T9720539
Position Surface form Disambiguated ID Type / Status
Subject Tuesday Weld E235451 entity
Predicate notableRole P22 FINISHED
Object Dorothy in Thief
Dorothy in *Thief* is the character portrayed by Tuesday Weld in Michael Mann’s 1981 neo-noir crime film *Thief*.
E816392 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: Dorothy in Thief | Statement: [Tuesday Weld, notableRole, Dorothy in Thief]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dorothy in Thief
Context triple: [Tuesday Weld, notableRole, Dorothy in Thief]
  • A. Valerie
    Valerie is a feminine given name of Latin origin, commonly associated with strength and valor.
  • B. Valerie
    "Valerie" is a 1957 American Western film starring Sterling Hayden, loosely inspired by the Rashomon-style multiple-perspective narrative.
  • C. Valerie
    "Valerie" is a song by the artist Rumble Doll.
  • D. Valerie
    Valerie is a sharp-tongued, quick-witted character in "The Princess Bride," known for helping her husband Miracle Max revive the hero Westley.
  • E. Kara Knack
    Kara Knack is best known as the former wife of American actor Pernell Roberts, who starred as Adam Cartwright on the classic TV series "Bonanza."
  • 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: Dorothy in Thief
Triple: [Tuesday Weld, notableRole, Dorothy in Thief]
Generated description
Dorothy in *Thief* is the character portrayed by Tuesday Weld in Michael Mann’s 1981 neo-noir crime film *Thief*.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Dorothy in Thief
Target entity description: Dorothy in *Thief* is the character portrayed by Tuesday Weld in Michael Mann’s 1981 neo-noir crime film *Thief*.
  • A. Valerie
    "Valerie" is a 1957 American Western film starring Sterling Hayden, loosely inspired by the Rashomon-style multiple-perspective narrative.
  • B. Valerie
    Valerie is a feminine given name of Latin origin, commonly associated with strength and valor.
  • C. Valerie
    "Valerie" is a song by the artist Rumble Doll.
  • D. Valerie
    Valerie is a sharp-tongued, quick-witted character in "The Princess Bride," known for helping her husband Miracle Max revive the hero Westley.
  • E. Kara Knack
    Kara Knack is best known as the former wife of American actor Pernell Roberts, who starred as Adam Cartwright on the classic TV series "Bonanza."
  • 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_69ca84d0123c819096f9dc3b6abb0881 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cd9e419c2c8190b325d5fd692c6000 completed April 1, 2026, 10:37 p.m.
NED1 Entity disambiguation (via context triple) batch_69d19fa130548190ae729487b90fa8a7 completed April 4, 2026, 11:32 p.m.
NEDg Description generation batch_69d1a0b4dbf8819097e38c253327fc10 completed April 4, 2026, 11:37 p.m.
NED2 Entity disambiguation (via description) batch_69d1a172ad848190a76f95c4937689d7 completed April 4, 2026, 11:40 p.m.
Created at: March 30, 2026, 8:20 p.m.