Triple

T7483390
Position Surface form Disambiguated ID Type / Status
Subject Kate Lardner E176817 entity
Predicate father P120 FINISHED
Object David Lardner
David Lardner was an American journalist and war correspondent for The New Yorker who was killed while covering World War II.
E689177 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: David Lardner | Statement: [Kate Lardner, father, David Lardner]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: David Lardner
Context triple: [Kate Lardner, father, David Lardner]
  • A. John Dolman
    John Dolman was an English clergyman and benefactor of the late 16th century best known for establishing Pocklington School in Yorkshire.
  • B. William Ashburner
    William Ashburner was a 19th-century American mining engineer and geologist known for his work in mineral surveying and resource assessment in the western United States.
  • C. Jonathan Latimer
    Jonathan Latimer was an American crime novelist and screenwriter known for his hardboiled detective fiction and for adapting works by authors like Dashiell Hammett for film.
  • D. Philip Christison
    Philip Christison was a British Army general who held senior commands in World War II, particularly in Southeast Asia.
  • E. John L. Lumley
    John L. Lumley was a prominent American fluid dynamicist known for his pioneering contributions to the understanding and modeling of turbulence.
  • 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: David Lardner
Triple: [Kate Lardner, father, David Lardner]
Generated description
David Lardner was an American journalist and war correspondent for The New Yorker who was killed while covering World War II.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: David Lardner
Target entity description: David Lardner was an American journalist and war correspondent for The New Yorker who was killed while covering World War II.
  • A. John Dolman
    John Dolman was an English clergyman and benefactor of the late 16th century best known for establishing Pocklington School in Yorkshire.
  • B. William Ashburner
    William Ashburner was a 19th-century American mining engineer and geologist known for his work in mineral surveying and resource assessment in the western United States.
  • C. Jonathan Latimer
    Jonathan Latimer was an American crime novelist and screenwriter known for his hardboiled detective fiction and for adapting works by authors like Dashiell Hammett for film.
  • D. Philip Christison
    Philip Christison was a British Army general who held senior commands in World War II, particularly in Southeast Asia.
  • E. John L. Lumley
    John L. Lumley was a prominent American fluid dynamicist known for his pioneering contributions to the understanding and modeling of turbulence.
  • 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_69c69f24ac508190bb98fe927c0bd065 completed March 27, 2026, 3:15 p.m.
NER Named-entity recognition batch_69c6f53923e4819081bf79ed962a971c completed March 27, 2026, 9:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8f30833588190a7217fdf160f2d49 completed March 29, 2026, 9:38 a.m.
NEDg Description generation batch_69c8f392edd8819089852a9fd71cc970 completed March 29, 2026, 9:40 a.m.
NED2 Entity disambiguation (via description) batch_69c8f48bdf1c8190aab34120be7b08e1 completed March 29, 2026, 9:44 a.m.
Created at: March 27, 2026, 3:42 p.m.