Triple

T8561937
Position Surface form Disambiguated ID Type / Status
Subject Maniac Mansion E202710 entity
Predicate artist P184 FINISHED
Object Gary Winnick E744009 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: Gary Winnick | Statement: [Maniac Mansion, artist, Gary Winnick]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gary Winnick
Context triple: [Maniac Mansion, artist, Gary Winnick]
  • A. Gary Winnick chosen
    Gary Winnick is an American game designer and artist best known for co-creating influential Lucasfilm Games adventures such as Maniac Mansion.
  • B. Jonathan David
    Jonathan David is a Canadian professional soccer forward known for his prolific goal-scoring for both the Canada national team and top European clubs.
  • C. Paulo Wanchope
    Paulo Wanchope is a retired Costa Rican striker known for his prolific goal-scoring in the English Premier League and for being one of Costa Rica’s most iconic footballers.
  • D. Nico Leunen
    Nico Leunen is a Belgian film editor known for his work on acclaimed international and arthouse films.
  • E. Cazorla
    Cazorla is a historic town in Andalusia, southern Spain, known as a gateway to the Sierra de Cazorla Natural Park and for its medieval castle and scenic mountain setting.
  • 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_69ca8326e6c881908ff720d6abaebdc5 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe94c0c3c8190aca981c07b090dc0 completed March 31, 2026, 3:33 p.m.
NED1 Entity disambiguation (via context triple) batch_69cebb84a6988190ba6852f72c8918ca completed April 2, 2026, 6:55 p.m.
Created at: March 30, 2026, 6:20 p.m.