Triple

T14120128
Position Surface form Disambiguated ID Type / Status
Subject John Darling E339881 entity
Predicate givenName P17 FINISHED
Object John
John is a fictional character from J.M. Barrie’s Peter Pan stories, known as one of the Darling children who travels to Neverland.
E1083646 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: John | Statement: [John Darling, givenName, John]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John
Context triple: [John Darling, givenName, John]
  • A. John
    John IV of Portugal was a 17th-century Portuguese king who restored the country's independence from Spain and founded the Braganza dynasty.
  • B. John
    John B. Magruder was a Confederate major general during the American Civil War, known for his leadership in the Peninsula Campaign and his flamboyant personality.
  • C. John
    John is the given name of John Hopfield, an American physicist and neuroscientist known for pioneering work on Hopfield networks in artificial intelligence.
  • D. John
    John of Brandenburg-Küstrin was a 16th-century German nobleman who ruled the Margraviate of Brandenburg-Küstrin and played a notable role in the politics of the Holy Roman Empire.
  • E. John
    John is a recurring comedic character from the British sketch show "A Bit of Fry & Laurie," portrayed in the series' distinctive absurd and witty style.
  • 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: John
Triple: [John Darling, givenName, John]
Generated description
John is a fictional character from J.M. Barrie’s Peter Pan stories, known as one of the Darling children who travels to Neverland.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: John
Target entity description: John is a fictional character from J.M. Barrie’s Peter Pan stories, known as one of the Darling children who travels to Neverland.
  • A. John
    John is the given name of Colonel John Parry, a fictional explorer and father of Lyra Belacqua in Philip Pullman’s "His Dark Materials" series.
  • B. John
    John is the first name of Squire Trelawney, a character from Robert Louis Stevenson’s classic adventure novel "Treasure Island."
  • C. John
    John is an alternative given name used by the character Jake Chambers, a central figure in Stephen King’s The Dark Tower series.
  • D. John
    John is the given name of the fictional character Trapper John McIntyre from the M*A*S*H franchise.
  • E. John
    John is the first name of the fictional character John Connor, the prophesied leader of the human resistance in the Terminator franchise.
  • 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_69d81c6a95b481909e39111e0c1f31ee completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de60942a588190beff0058a92f7051 completed April 14, 2026, 3:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcf7d863ac819085bf5cd76cb2e8dd completed May 7, 2026, 8:36 p.m.
NEDg Description generation batch_69fd0070ded48190a2cd1a1f95a48d13 completed May 7, 2026, 9:13 p.m.
NED2 Entity disambiguation (via description) batch_69fd012728788190b45639644e83afee completed May 7, 2026, 9:16 p.m.
Created at: April 9, 2026, 10:22 p.m.