Triple

T15996823
Position Surface form Disambiguated ID Type / Status
Subject Fred Savage E387988 entity
Predicate notableWork P4 FINISHED
Object Working E288287 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: Working | Statement: [Fred Savage, notableWork, Working]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Working
Context triple: [Fred Savage, notableWork, Working]
  • A. Working chosen
    "Working" is a musical by Stephen Schwartz that adapts Studs Terkel’s book of interviews into a series of vignettes exploring the lives and aspirations of everyday American workers.
  • B. Work
    Work is an abstract intellectual or artistic creation that exists independently of any particular physical or digital manifestation.
  • C. Workmore
    Workmore is a small unincorporated rural community located in Telfair County, Georgia, United States.
  • D. Working Designs
    Working Designs was an American video game publisher best known for its high-quality, humor-infused localizations of Japanese role-playing games in the 1990s.
  • E. Prace
    Prace is a small village in the South Moravian Region of the Czech Republic, known for its proximity to the historic town of Slavkov u Brna (Austerlitz).
  • 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_69d86daa562c81908aacc179c0fe8fb5 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e157882ef0819081143e530bd6413c completed April 16, 2026, 9:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffc3d79dec8190b02e003f93e5dad6 completed May 9, 2026, 11:31 p.m.
Created at: April 10, 2026, 4:55 a.m.