Triple

T17228978
Position Surface form Disambiguated ID Type / Status
Subject John Harsanyi E418194 entity
Predicate givenName P17 FINISHED
Object John
John is the given name of John Harsanyi, a Nobel Prize–winning economist known for his contributions to game theory and the analysis of games with incomplete information.
E1258118 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 Harsanyi, givenName, John]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John
Context triple: [John Harsanyi, givenName, John]
  • A. John
    John is the given name of John A. Roebling II, an American civil engineer and philanthropist from the prominent Roebling family associated with major bridge construction.
  • B. John
    John is the given first name of Johnny Kilbane, an American featherweight boxing champion from the early 20th century.
  • C. John
    John is the first name of Jack Phillips, the British wireless operator on the RMS Titanic who died during its sinking in 1912.
  • D. John
    John is the given name of John Bowen, a British novelist and playwright known for his crime and speculative fiction.
  • E. John
    John is the given name of John Maitland, 1st Duke of Lauderdale, a prominent 17th-century Scottish nobleman and statesman.
  • 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 Harsanyi, givenName, John]
Generated description
John is the given name of John Harsanyi, a Nobel Prize–winning economist known for his contributions to game theory and the analysis of games with incomplete information.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: John
Target entity description: John is the given name of John Harsanyi, a Nobel Prize–winning economist known for his contributions to game theory and the analysis of games with incomplete information.
  • A. John
    John is the given name of the influential American economist John Bates Clark, known for his work on marginal productivity theory.
  • B. John
    John is the given name of John Polanyi, a Nobel Prize–winning chemist known for his work on chemical kinetics and reaction dynamics.
  • 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 is the given name of John B. Fenn, the American chemist and Nobel laureate known for his work in electrospray ionization mass spectrometry.
  • E. John
    John is the given name of the renowned British mathematician John H. Conway, known for his work in group theory, number theory, and the invention of the Game of Life.
  • 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_69d886d8e96081909870bff6c3d0bf09 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e42df55e788190b442ffd4fac768c9 completed April 19, 2026, 1:20 a.m.
NED1 Entity disambiguation (via context triple) batch_6a01674df2cc8190be602b15d49d38d0 completed May 11, 2026, 5:21 a.m.
NEDg Description generation batch_6a016c03dab88190926c36f2e6b55861 completed May 11, 2026, 5:41 a.m.
NED2 Entity disambiguation (via description) batch_6a016cba568481908920fe42cae5f153 completed May 11, 2026, 5:44 a.m.
Created at: April 10, 2026, 5:39 a.m.