Triple

T20296531
Position Surface form Disambiguated ID Type / Status
Subject The Girl and Her Trust E505366 entity
Predicate starring P1507 FINISHED
Object Charles Craig
Charles Craig was an early 20th-century actor known for his work in silent films.
E1423539 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: Charles Craig | Statement: [The Girl and Her Trust, starring, Charles Craig]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Charles Craig
Context triple: [The Girl and Her Trust, starring, Charles Craig]
  • A. John Graham
    John Graham is an Australian Labor Party politician who serves as a senior minister in the New South Wales government under Premier Chris Minns.
  • B. John Graham
    John Graham was a British colonial military officer after whom the South African town of Grahamstown (now Makhanda) was named.
  • C. Anthony Read
    Anthony Read was a British television writer and script editor best known for his work on the science fiction series Doctor Who and various other BBC dramas.
  • D. Joe Royall
    Joe Royall is an individual recognized as a notable bearer of the surname Royall.
  • E. John Lyons
    John Lyons is a film producer known for his work on the acclaimed documentary "All the Beauty and the Bloodshed."
  • 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: Charles Craig
Triple: [The Girl and Her Trust, starring, Charles Craig]
Generated description
Charles Craig was an early 20th-century actor known for his work in silent films.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Charles Craig
Target entity description: Charles Craig was an early 20th-century actor known for his work in silent films.
  • A. John Graham
    John Graham is an Australian Labor Party politician who serves as a senior minister in the New South Wales government under Premier Chris Minns.
  • B. John Graham
    John Graham was a British colonial military officer after whom the South African town of Grahamstown (now Makhanda) was named.
  • C. Anthony Read
    Anthony Read was a British television writer and script editor best known for his work on the science fiction series Doctor Who and various other BBC dramas.
  • D. Joe Royall
    Joe Royall is an individual recognized as a notable bearer of the surname Royall.
  • E. John Lyons
    John Lyons is a film producer best known for his work on major Hollywood comedies, including the Austin Powers series.
  • 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_69e0b4b8ab648190906e18538c250148 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e67707f770819093742d7509fe9bdd completed April 20, 2026, 6:57 p.m.
NED1 Entity disambiguation (via context triple) batch_6a08611590b481909235d7bbec2387bd completed May 16, 2026, 12:20 p.m.
NEDg Description generation batch_6a086282203881908726f58843a8ae5d completed May 16, 2026, 12:26 p.m.
NED2 Entity disambiguation (via description) batch_6a08638b64a88190a068a2d0c15dc448 completed May 16, 2026, 12:31 p.m.
Created at: April 16, 2026, 11:15 a.m.