Triple

T16744790
Position Surface form Disambiguated ID Type / Status
Subject Louis Tully E406923 entity
Predicate friendOf P8712 FINISHED
Object Winston Zeddemore E377581 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: Winston Zeddemore | Statement: [Louis Tully, friendOf, Winston Zeddemore]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Winston Zeddemore
Context triple: [Louis Tully, friendOf, Winston Zeddemore]
  • A. Winston Zeddemore chosen
    Winston Zeddemore is one of the core members of the Ghostbusters team, known as the down-to-earth everyman who joins the group as their fourth ghost hunter.
  • B. Morrow Wilson
    Morrow Wilson is an American actor and writer best known as the longtime husband of Golden Girls star Rue McClanahan.
  • C. Barrett Doss
    Barrett Doss is an American actress and singer best known for her starring role as firefighter Victoria Hughes on the television drama series "Station 19."
  • D. Zeke Hawkins
    Zeke Hawkins is a central character in the science fiction horror film "Sliver."
  • E. Ned Willard
    Ned Willard is the central protagonist of Ken Follett’s historical novel "A Column of Fire," a resourceful Englishman whose life and loyalties are tested amid the religious and political turmoil of 16th-century Europe.
  • 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_69d8838ffb088190a0b11149929006bf completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3aa210ef88190be74bd60d7144953 completed April 18, 2026, 3:58 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00a51e69c08190a5bff74823df430c completed May 10, 2026, 3:32 p.m.
Created at: April 10, 2026, 5:21 a.m.