Triple

T15280090
Position Surface form Disambiguated ID Type / Status
Subject Eighth Doctor E365244 entity
Predicate companion P2932 FINISHED
Object Molly O’Sullivan E1143576 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: Molly O’Sullivan | Statement: [Eighth Doctor, companion, Molly O’Sullivan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Molly O’Sullivan
Context triple: [Eighth Doctor, companion, Molly O’Sullivan]
  • A. Siobhan Walsh
    Siobhan Walsh is an Irish humanitarian and development leader known for her work with international aid organizations and efforts to combat global poverty and hunger.
  • B. Emma Cunniffe chosen
    Emma Cunniffe is a British actress known for her work in television dramas, theatre, and film.
  • C. Siobhan Reilly
    Siobhan Reilly is an actress known for her role in the Scottish comedy-drama film "The Angels' Share."
  • D. Molly McCauley
    Molly McCauley, better known as Molly Pitcher, is a legendary figure of the American Revolutionary War celebrated for taking her husband's place at a cannon during the Battle of Monmouth.
  • E. Sarah O'Connell
    Sarah O'Connell is the wife of British-Australian radio presenter and comedian Christian O'Connell.
  • 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_69d85a103d9081908c1ea6c4c73ac8e3 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e00e504d8c8190ad6c565a31d1a9bd completed April 15, 2026, 10:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69ff21945b60819098ea91d9693cb8e3 completed May 9, 2026, 11:59 a.m.
Created at: April 10, 2026, 3:15 a.m.