Triple

T7
Position Surface form Disambiguated ID Type / Status
Subject Vannevar Bush E0 entity
Predicate givenName P17 FINISHED
Object Vannevar E0 NE FINISHED

How this triple was built (3 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: Vannevar | Statement: [Vannevar Bush, givenName, Vannevar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Vannevar
Context triple: [Vannevar Bush, givenName, Vannevar]
  • A. Vannevar Bush chosen
    American electrical engineer and science administrator (1890~1974)
  • B. Douglas Engelbart
    Douglas Engelbart was an American engineer and inventor best known for pioneering the computer mouse and groundbreaking concepts in interactive computing and hypertext that helped shape modern personal computing.
  • C. Ted Nelson
    Ted Nelson is an American pioneer of information technology best known for coining the term "hypertext" and envisioning non-linear, interconnected digital documents.
  • D. Office of Scientific Research and Development
    The Office of Scientific Research and Development was a U.S. government agency during World War II that coordinated military-related scientific research, including major projects like the development of radar and the atomic bomb.
  • E. Differential analyzer
    The Differential Analyzer is an early analog mechanical computer designed to solve differential equations using interconnected rotating shafts and wheels.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: givenName
Context triple: [Vannevar Bush, givenName, Vannevar]
  • A. instanceOf
    relation of type constraints
  • 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_69a1c42f421881909e892cd3c0b8a381 completed Feb. 27, 2026, 4:19 p.m.
NER Named-entity recognition batch_69a1d89696a48190a0334ff9cb1416ad completed Feb. 27, 2026, 5:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69a22a2f86ec81908e07bdf92a20b9ae completed Feb. 27, 2026, 11:35 p.m.
PD Predicate disambiguation batch_69a1c97e9dac8190a5a8e320b8620755 completed Feb. 27, 2026, 4:42 p.m.
PDg Predicate description generation batch_69a1d895cb208190973a67179da8b4cf completed Feb. 27, 2026, 5:47 p.m.
Created at: Feb. 27, 2026, 4:42 p.m.