Triple

T9898623
Position Surface form Disambiguated ID Type / Status
Subject OData E182234 entity
Predicate hasPart P35 FINISHED
Object OData Atom Format E182234 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: OData Atom Format | Statement: [OData, hasPart, OData Atom Format]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: OData Atom Format
Context triple: [OData, hasPart, OData Atom Format]
  • A. OData chosen
    OData (Open Data Protocol) is a standardized, REST-based protocol for querying and updating data over the web, commonly used to expose and consume interoperable APIs.
  • B. WADL
    WADL is the ICAO airport code for Lombok International Airport in Indonesia.
  • C. OAI-PMH
    OAI-PMH (Open Archives Initiative Protocol for Metadata Harvesting) is a low-barrier protocol used to collect and share metadata from repositories to enable interoperable discovery of scholarly and other digital resources.
  • D. Resource Description Framework in Attributes
    Resource Description Framework in Attributes (RDFa) is a W3C recommendation that extends HTML and other web documents with attributes for embedding structured, machine-readable metadata directly into human-readable content.
  • E. Office Open XML (ECMA-376)
    Office Open XML (ECMA-376) is a standardized, XML-based file format used primarily by Microsoft Office applications for representing word processing documents, spreadsheets, and presentations.
  • 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_69d1eb1b9534819093c5150f1ed8f685 completed April 5, 2026, 4:54 a.m.
Created at: March 30, 2026, 8:40 p.m.