Triple

T20183419
Position Surface form Disambiguated ID Type / Status
Subject Killing Zoe E492790 entity
Predicate mainCharacter P1183 FINISHED
Object Zed
Zed is the central protagonist of the crime film "Killing Zoe," a professional safecracker drawn into a violent Parisian bank heist.
 E1415795 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: Zed | Statement: [Killing Zoe, mainCharacter, Zed]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Zed
Context triple: [Killing Zoe, mainCharacter, Zed]
  • A. Zed
    Zed is the rebellious Exterminator protagonist played by Sean Connery in the 1974 science fiction film "Zardoz."
  • B. Zed
    Zed is the stern, no-nonsense head of the secret government agency overseeing extraterrestrial activity in the "Men in Black" film series.
  • C. Zan
    Zan is a collective term for a group of closely related Kartvelian languages spoken primarily in western Georgia, including Mingrelian and Laz.
  • D. Zedus
    Zedus is a giant, reptilian kaiju antagonist from the film "Gamera the Brave," known for battling the young Gamera.
  • E. Zev
    Zev is a masculine given name of Hebrew origin, commonly interpreted to mean "wolf."
  • 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: Zed
Triple: [Killing Zoe, mainCharacter, Zed]
Generated description
Zed is the central protagonist of the crime film "Killing Zoe," a professional safecracker drawn into a violent Parisian bank heist.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Zed
Target entity description: Zed is the central protagonist of the crime film "Killing Zoe," a professional safecracker drawn into a violent Parisian bank heist.
  • A. Zed
    Zed is the stern, no-nonsense head of the secret government agency overseeing extraterrestrial activity in the "Men in Black" film series.
  • B. Zed
    Zed is the rebellious Exterminator protagonist played by Sean Connery in the 1974 science fiction film "Zardoz."
  • C. Zan
    Zan is a collective term for a group of closely related Kartvelian languages spoken primarily in western Georgia, including Mingrelian and Laz.
  • D. Zedus
    Zedus is a giant, reptilian kaiju antagonist from the film "Gamera the Brave," known for battling the young Gamera.
  • E. Zev
    Zev is a masculine given name of Hebrew origin, commonly interpreted to mean "wolf."
  • 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_69da6268a034819081cbd9ea5a1c9475 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e668f068748190a0941e98ef5afd59 completed April 20, 2026, 5:57 p.m.
NED1 Entity disambiguation (via context triple) batch_6a083c7febf8819091f9b551b3d3b779 completed May 16, 2026, 9:44 a.m.
NEDg Description generation batch_6a083d3196148190847a625ad09762a2 completed May 16, 2026, 9:47 a.m.
NED2 Entity disambiguation (via description) batch_6a083e04aab88190a1e0219427d8d0e1 completed May 16, 2026, 9:51 a.m.
Created at: April 11, 2026, 11:36 p.m.