Triple

T11117580
Position Surface form Disambiguated ID Type / Status
Subject Adam (Rodin) E262927 entity
Predicate hasPartOrVersion P35 FINISHED
Object Adam (plaster version) E262927 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: Adam (plaster version) | Statement: [Adam (Rodin), hasPartOrVersion, Adam (plaster version)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Adam (plaster version)
Context triple: [Adam (Rodin), hasPartOrVersion, Adam (plaster version)]
  • A. ADAM
    ADAM is the former name for Microsoft’s lightweight, standalone directory service now known as Active Directory Lightweight Directory Services (AD LDS), used for directory-enabled applications without requiring a full Active Directory domain.
  • B. Adam chosen
    Adam is a renowned sculpture by Auguste Rodin, notable for its expressive depiction of the biblical figure and housed in the Rodin Museum.
  • C. Adam
    Adam is a common surname of Scottish and English origin, borne by various notable individuals including architects, politicians, and artists.
  • D. Adam
    Adam is a popular stochastic optimization algorithm widely used to train deep learning models by adaptively adjusting learning rates for each parameter.
  • E. Adam
    Adam is a widely used stochastic optimization algorithm in machine learning that combines ideas from momentum and adaptive learning rates to efficiently train deep neural networks.
  • 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: hasPartOrVersion
Context triple: [Adam (Rodin), hasPartOrVersion, Adam (plaster version)]
  • A. hasPart chosen
    Indicates that one entity is a component, segment, or constituent part of another entity.
  • B. hasVersionIn
    Indicates that one entity exists as a specific version or variant within the context, format, or system represented by another entity.
  • C. hasMultipleVersions
    Indicates that an entity exists in more than one distinct version or revision.
  • D. hasPartIn
    Indicates that an entity participates in or plays a role within a larger event, process, or composite entity.
  • E. hasPartInLegacy
    Indicates that an entity includes another entity as a component or constituent specifically within its legacy or historically inherited structure.
  • F. None of above.

Provenance (4 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_69d6aa9b46cc8190b19f9f0cc45bf322 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d79af638b08190b7ade5eb0cab6b75 completed April 9, 2026, 12:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69e42d8084a88190918f1f94ca0119ed completed April 19, 2026, 1:18 a.m.
PD Predicate disambiguation batch_69d7441cf8188190b8095f622c923156 completed April 9, 2026, 6:15 a.m.
Created at: April 8, 2026, 9:27 p.m.