Triple

T17569449
Position Surface form Disambiguated ID Type / Status
Subject Ben Alman E427896 entity
Predicate name P16 FINISHED
Object Ben Alman NE NERFINISHED

How this triple was built (2 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: Ben Alman | Statement: [Ben Alman, name, Ben Alman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ben Alman
Context triple: [Ben Alman, name, Ben Alman]
  • A. Ben Alman chosen
    Ben Alman is a software developer best known for creating the JavaScript task runner Grunt and contributing widely to open-source tooling.
  • B. Douglas Crockford
    Douglas Crockford is an American computer programmer and author best known for popularizing the JSON data format and contributing to JavaScript language development and style guidelines.
  • C. Eric Jumper
    Eric Jumper is an American engineer and researcher best known for his pioneering scientific investigations into the Shroud of Turin as part of the Shroud of Turin Research Project.
  • D. Ian Hickson
    Ian Hickson is a prominent web standards editor and software engineer best known for his leading role in developing the HTML5 specification and his work with the WHATWG and W3C.
  • E. Jesse James Garrett
    Jesse James Garrett is an American user experience designer and author best known for coining the term AJAX and influencing modern web application design.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d889e0385081908a04b66f4dd4bd0d completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e4592fe8408190bd8fed1920ab3601 completed April 19, 2026, 4:25 a.m.
Created at: April 10, 2026, 5:50 a.m.