Triple

T1425021
Position Surface form Disambiguated ID Type / Status
Subject Charles Goldfarb E30309 entity
Predicate employer P7 FINISHED
Object IBM E1102 NE FINISHED

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: IBM | Statement: [Charles Goldfarb, employer, IBM]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: IBM
Context triple: [Charles Goldfarb, employer, IBM]
  • A. IBM chosen
    IBM is a multinational technology and consulting company known for its pioneering work in computer hardware, software, and enterprise services.
  • B. Hewlett-Packard
    Hewlett-Packard is a pioneering American technology company known for its innovations in computing, printers, and enterprise IT solutions.
  • C. Sun Microsystems
    Sun Microsystems was a pioneering American technology company best known for developing the Java programming language, the Solaris operating system, and high-performance networked computer systems.
  • D. Dell
    Dell is a major American technology company best known for designing, manufacturing, and selling personal computers, servers, and related IT products and services worldwide.
  • E. Compaq
    Compaq was a major American computer company best known for its popular line of personal computers and for being one of the largest PC manufacturers before its acquisition by Hewlett-Packard.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69a498fb823c8190a67ce4c4837e641a completed March 1, 2026, 7:52 p.m.
NER Named-entity recognition batch_69a4c4bd59148190b96f9f585e07aa0d completed March 1, 2026, 10:59 p.m.
NED1 Entity disambiguation (via context triple) batch_69ad08b35da08190b8c09ad393f310e3 completed March 8, 2026, 5:27 a.m.
Created at: March 1, 2026, 8 p.m.