Triple

T2965022
Position Surface form Disambiguated ID Type / Status
Subject Mikael Salomon E80140 entity
Predicate workedOn P3 FINISHED
Object Always E120038 NE 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: Always | Statement: [Mikael Salomon, workedOn, Always]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Always
Context triple: [Mikael Salomon, workedOn, Always]
  • A. Always chosen
    "Always" is a 1989 romantic fantasy film directed by Steven Spielberg, starring Richard Dreyfuss as a deceased pilot who returns as a spirit to guide his former lover and a young aviator.
  • B. Always
    "Always" is a popular romantic song written by American composer Irving Berlin in 1925, often remembered as a classic standard of early 20th-century American music.
  • C. Always
    "Always" is a power ballad by American rock band Bon Jovi, released in 1994 and known as one of their biggest global hits.
  • D. Sempre sempre
    "Sempre sempre" is a popular Italian song performed by Romina Power (with Al Bano), known as one of the duo’s signature romantic hits.
  • E. Constant
    Constant is a character in John Vanbrugh’s Restoration comedy "The Provoked Wife," serving as one of the play’s central figures in its exploration of marriage, desire, and social manners.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69ad8b1341848190bd19dbf46892887d completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad9958b1e48190a77f37bf63333c5b completed March 8, 2026, 3:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69b0fc9bc190819087cb35ee7c78825a completed March 11, 2026, 5:24 a.m.
Created at: March 8, 2026, 2:58 p.m.