Triple

T10890481
Position Surface form Disambiguated ID Type / Status
Subject Emma Donoghue E257159 entity
Predicate notableWork P4 FINISHED
Object Room E554407 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: Room | Statement: [Emma Donoghue, notableWork, Room]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Room
Context triple: [Emma Donoghue, notableWork, Room]
  • A. Room
    "Room" is a notable work by Danny Cohen, likely recognized as a significant contribution within his creative or professional field.
  • B. Room
    "Room" is a solo studio album by American actress and singer Katey Sagal, showcasing her blend of rock, country, and blues influences.
  • C. Room chosen
    Room is a 2015 drama film, directed by Lenny Abrahamson and acclaimed for its intense, intimate portrayal of a mother and son held in captivity and their struggle to adjust to the outside world.
  • D. Rooms
    Rooms is a section of Gertrude Stein’s experimental modernist work "Tender Buttons," characterized by its fragmented, poetic prose exploring everyday domestic spaces.
  • E. Room 25
    Room 25 is a science-fiction themed board game in which players attempt to escape a deadly, ever-shifting prison complex while navigating hidden roles and cooperative or semi-cooperative objectives.
  • 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_69d6aa848804819081b2713ca0bedf06 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d752041e2c8190b513dc9dc5857fcc completed April 9, 2026, 7:15 a.m.
NED1 Entity disambiguation (via context triple) batch_69e15500bb7881908b9799d7653aec72 completed April 16, 2026, 9:30 p.m.
Created at: April 8, 2026, 9:21 p.m.