Triple

T8076166
Position Surface form Disambiguated ID Type / Status
Subject Shot Sage Blue Marilyn E188495 entity
Predicate seriesSize P80358 FINISHED
Object 4 paintings in the Shot Marilyns series LITERAL 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: 4 paintings in the Shot Marilyns series | Statement: [Shot Sage Blue Marilyn, seriesSize, 4 paintings in the Shot Marilyns series]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: seriesSize
Context triple: [Shot Sage Blue Marilyn, seriesSize, 4 paintings in the Shot Marilyns series]
  • A. numberOfSeries
    Indicates the total count of distinct series associated with or contained within a given entity.
  • B. seriesScale
    Indicates that one value or measurement is expressed relative to another according to a defined proportional scale within a series.
  • C. seriesBy
    Indicates that one entity is the creator, author, or originator of a series to which the other entity belongs.
  • D. seriesOf
    Indicates that one entity is a sequence or ordered set of related items, events, or parts that collectively form or belong to another entity.
  • E. hasSeriesNumber
    Indicates that an entity is assigned a specific ordinal or sequence number within a series or ordered set.
  • F. None of above. chosen

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_69ca82b50c708190863f661d438e68df completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb404dc7ac8190956b5c2f5aeac6b2 completed March 31, 2026, 3:32 a.m.
PD Predicate disambiguation batch_69cb049f1614819087360d1a4c6f0faa completed March 30, 2026, 11:17 p.m.
PDg Predicate description generation batch_69cb14be17208190bb51c3dfcb613f20 completed March 31, 2026, 12:26 a.m.
Created at: March 30, 2026, 5:28 p.m.