Triple

T2273990
Position Surface form Disambiguated ID Type / Status
Subject Bullitt E50725 entity
Predicate editedBy P1954 FINISHED
Object Frank P. Keller
Frank P. Keller is a film editor best known for his Academy Award-winning work on the 1968 action film "Bullitt."
 E373275 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: Frank P. Keller | Statement: [Bullitt, editedBy, Frank P. Keller]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Frank P. Keller
Context triple: [Bullitt, editedBy, Frank P. Keller]
  • A. Frederick W. Lander
    Frederick W. Lander was a 19th-century American civil engineer and explorer best known for surveying and constructing overland wagon routes to the western United States.
  • B. Charles J.D. Schlissel
    Charles J.D. Schlissel is a film producer best known for his work on major Hollywood thrillers such as "Flightplan."
  • C. Donald W. Loveland
    Donald W. Loveland is a logician and computer scientist known for his influential contributions to automated theorem proving and logic in computer science.
  • D. Donald F. Hornig
    Donald F. Hornig was an American chemist and science advisor who served as a key presidential science counselor, notably to President Lyndon B. Johnson.
  • E. Robert N. Fitch
    Robert N. Fitch was a composer best known for writing the University of California fight song "Fight for California."
  • 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: Frank P. Keller
Triple: [Bullitt, editedBy, Frank P. Keller]
Generated description
Frank P. Keller is a film editor best known for his Academy Award-winning work on the 1968 action film "Bullitt."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Frank P. Keller
Target entity description: Frank P. Keller is a film editor best known for his Academy Award-winning work on the 1968 action film "Bullitt."
  • A. Frederick W. Lander
    Frederick W. Lander was a 19th-century American civil engineer and explorer best known for surveying and constructing overland wagon routes to the western United States.
  • B. Charles J.D. Schlissel
    Charles J.D. Schlissel is a film producer best known for his work on major Hollywood thrillers such as "Flightplan."
  • C. Donald W. Loveland
    Donald W. Loveland is a logician and computer scientist known for his influential contributions to automated theorem proving and logic in computer science.
  • D. Donald F. Hornig
    Donald F. Hornig was an American chemist and science advisor who served as a key presidential science counselor, notably to President Lyndon B. Johnson.
  • E. Robert N. Fitch
    Robert N. Fitch was a composer best known for writing the University of California fight song "Fight for California."
  • 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_69a88b05910c8190a9a2b1ff230c85f9 completed March 4, 2026, 7:41 p.m.
NER Named-entity recognition batch_69abc1ea6cc88190982527774223127f completed March 7, 2026, 6:12 a.m.
NED1 Entity disambiguation (via context triple) batch_69b432e588308190bd331d7b8776e546 completed March 13, 2026, 3:53 p.m.
NEDg Description generation batch_69b436c3d6a0819081478d3cafb6f40b completed March 13, 2026, 4:09 p.m.
NED2 Entity disambiguation (via description) batch_69b43725f4108190b8f19fc730b72d98 completed March 13, 2026, 4:11 p.m.
Created at: March 4, 2026, 7:48 p.m.