Triple

T9898162
Position Surface form Disambiguated ID Type / Status
Subject ECMA E182225 entity
Predicate standardNumber P4626 FINISHED
Object ECMA-334 E34645 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: ECMA-334 | Statement: [ECMA, standardNumber, ECMA-334]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ECMA-334
Context triple: [ECMA, standardNumber, ECMA-334]
  • A. ECMA-334 chosen
    ECMA-334 is the ECMA International standard that formally defines the C# programming language specification.
  • B. ECMA-340
    ECMA-340 is an international standard that specifies the Near Field Communication (NFC) interface and protocol for short-range wireless communication between electronic devices.
  • C. ECMA-372
    ECMA-372 is the ECMA standard that defines the C++/CLI language specification for managed extensions of C++ targeting the .NET runtime.
  • D. ECMA-367
    ECMA-367 is the official international standard that defines the syntax and semantics of the Eiffel programming language.
  • E. Ecma TC45
    Ecma TC45 is the Ecma International technical committee responsible for standardizing and evolving the Office Open XML document formats.
  • 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_69ca82876f8081909cf75df0f99bb13f completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cdb4ac27d88190b8255f7e616f95c9 completed April 2, 2026, 12:13 a.m.
NED1 Entity disambiguation (via context triple) batch_69d1eb17ed548190a2510a667dd988ca completed April 5, 2026, 4:54 a.m.
Created at: March 30, 2026, 8:40 p.m.