Triple

T13539311
Position Surface form Disambiguated ID Type / Status
Subject Sissy Rommely E323340 entity
Predicate auntOf P3525 FINISHED
Object Laurie Nolan E445752 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: Laurie Nolan | Statement: [Sissy Rommely, auntOf, Laurie Nolan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Laurie Nolan
Context triple: [Sissy Rommely, auntOf, Laurie Nolan]
  • A. Laurie Nolan chosen
    Laurie Nolan is the child of American sports personality and media host Katie Nolan.
  • B. Laurie Lennard
    Laurie Lennard, also known as Laurie David, is an American environmental activist and film producer recognized for her work on climate change documentaries such as "An Inconvenient Truth."
  • C. Laurie Morton
    Laurie Morton is known as the spouse of Australian actor and producer David Kelly.
  • D. Laurie Ronson
    Laurie Ronson is the mother of British-American musician and producer Mark Ronson.
  • E. Laurie Holmes
    Laurie Holmes is best known as the widow of legendary adult film actor John Holmes and for managing his estate and legacy after his death.
  • 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_69d8076776248190bdf0d4fa1f85a5fc completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbafd7ad9481908fe1d7ffcf8fab71 completed April 12, 2026, 2:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd54f5323c8190aa239bad461b0857 completed May 8, 2026, 3:13 a.m.
Created at: April 9, 2026, 9:45 p.m.