Triple

T25804426
Position Surface form Disambiguated ID Type / Status
Subject Tom Avery E649925 entity
Predicate isGrieving P44213 FINISHED
Object death of his son 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: death of his son | Statement: [Tom Avery, isGrieving, death of his son]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: isGrieving
Context triple: [Tom Avery, isGrieving, death of his son]
  • A. mourningLevel
    Indicates the degree or intensity to which an entity is experiencing or expressing mourning in response to a loss.
  • B. grievesFor chosen
    Indicates that one entity feels grief or sorrow because of the loss, suffering, or misfortune of another entity.
  • C. mourningIntensifiesIn
    Indicates that the level or expression of mourning becomes stronger or more intense within a specified context, period, or situation.
  • D. mourningPeriodBegins
    Indicates that the formal period of mourning for a death or loss has started.
  • E. mourningCause
    Indicates that one entity is in a state of mourning specifically because of the other entity, which is the cause or reason for the grief.
  • F. None of above.

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_69e7ab35d264819095367f7e80c983ff completed April 21, 2026, 4:52 p.m.
NER Named-entity recognition batch_69f5ffcdc66c8190a7aa2f1bdfe01f98 completed May 2, 2026, 1:44 p.m.
PD Predicate disambiguation batch_69f4938b960081909b53c074a3e0c7c2 completed May 1, 2026, 11:50 a.m.
Created at: April 22, 2026, 7:01 a.m.