Triple

T10811990
Position Surface form Disambiguated ID Type / Status
Subject Two Tickets to London E255124 entity
Predicate castMember P1668 FINISHED
Object Lumsden Hare E867642 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: Lumsden Hare | Statement: [Two Tickets to London, castMember, Lumsden Hare]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lumsden Hare
Context triple: [Two Tickets to London, castMember, Lumsden Hare]
  • A. Lumsden Hare chosen
    Lumsden Hare was an Irish-born actor and director known for his prolific work on stage and in early 20th-century British and American films.
  • B. Aspen Hare
    Aspen Hare is one of the official mascots of the 2002 Winter Olympics in Salt Lake City, representing speed and agility.
  • C. Lepus
    Lepus is a small southern constellation located just below Orion, traditionally representing a hare.
  • D. Lepus
    Lepus is a genus of fast-running mammals commonly known as hares and jackrabbits, found across much of the world in open and semi-open habitats.
  • E. Lepus victoriae
    Lepus victoriae, commonly known as the African savanna hare, is a species of hare native to sub-Saharan Africa, typically inhabiting open grasslands and savannas.
  • 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_69d6aa61c15c8190a1839550c56e75e1 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d733eadda48190b2b1183ee60102cb completed April 9, 2026, 5:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69de853692f08190914cbeaf1a558730 completed April 14, 2026, 6:19 p.m.
Created at: April 8, 2026, 9:18 p.m.