Triple

T20438880
Position Surface form Disambiguated ID Type / Status
Subject YBAs E501328 entity
Predicate collectorSupport P140133 FINISHED
Object strongly supported by Charles Saatchi 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: strongly supported by Charles Saatchi | Statement: [YBAs, collectorSupport, strongly supported by Charles Saatchi]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: collectorSupport
Context triple: [YBAs, collectorSupport, strongly supported by Charles Saatchi]
  • A. collectorStatus
    Indicates the current operational or lifecycle state of a collector in relation to its collection activity.
  • B. collectorInstruction
    Indicates that one entity provides specific directions or guidelines to a collector entity about how to perform a collection-related task or process.
  • C. collectorInterest
    Indicates that one entity has a special interest in acquiring, owning, or seeking out another entity as part of a collection.
  • D. collectionCompiler
    Indicates that an entity is responsible for compiling, assembling, or building a collection from its constituent elements or sources.
  • E. collectorIssueComposition
    Indicates that a collector’s issue or edition is composed of, or includes, specific constituent parts or items.
  • 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_69e0b4ab3cfc8190ac9bf32e932316b1 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e685f112e48190a3af818c0f6ee839 completed April 20, 2026, 8 p.m.
PD Predicate disambiguation batch_69e5766df0008190a73c4f613c29678f completed April 20, 2026, 12:42 a.m.
PDg Predicate description generation batch_69e58d766b408190a1d3698145fb6d30 completed April 20, 2026, 2:20 a.m.
Created at: April 16, 2026, 11:31 a.m.