Triple

T33160810
Position Surface form Disambiguated ID Type / Status
Subject Principe Island E848726 entity
Predicate observationHelpedConfirm P176999 FINISHED
Object gravitational deflection of light by the Sun 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: gravitational deflection of light by the Sun | Statement: [Principe Island, observationHelpedConfirm, gravitational deflection of light by the Sun]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: observationHelpedConfirm
Context triple: [Principe Island, observationHelpedConfirm, gravitational deflection of light by the Sun]
  • A. observationBenefit
    Indicates that one entity gains an advantage, insight, or positive outcome as a result of observing another entity or phenomenon.
  • B. observationType
    Indicates the specific kind or category of observation being made or recorded in a given context.
  • C. observation
    Indicates that one entity perceives, monitors, or takes note of another entity or phenomenon, typically to gather information about it.
  • D. observerStatusIn
    Indicates that an entity’s status or role is defined or valid within a specified observational context, system, or environment.
  • E. observationNote
    Indicates that there is an associated free-text comment or remark providing additional details or context about an observation.
  • 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_69f3495b02d08190bb3d366823dffc21 completed April 30, 2026, 12:21 p.m.
NER Named-entity recognition batch_69f6f85bfba48190aba95b40642a8ca7 completed May 3, 2026, 7:25 a.m.
PD Predicate disambiguation batch_69f6f6619404819084662aef1238261c completed May 3, 2026, 7:16 a.m.
PDg Predicate description generation batch_69f6f814fcf48190ae4504154d1b2c05 completed May 3, 2026, 7:24 a.m.
Created at: May 1, 2026, 1:28 a.m.