Triple

T9340820
Position Surface form Disambiguated ID Type / Status
Subject Jackie Earle Haley E224758 entity
Predicate characterPortrayed P1507 FINISHED
Object Walter Kovacs E792661 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: Walter Kovacs | Statement: [Jackie Earle Haley, characterPortrayed, Walter Kovacs]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Walter Kovacs
Context triple: [Jackie Earle Haley, characterPortrayed, Walter Kovacs]
  • A. Walter Joseph Kovacs chosen
    Walter Joseph Kovacs is the uncompromising, vigilante antihero behind the mask of Rorschach in the graphic novel "Watchmen."
  • B. Andrew Laszlo
    Andrew Laszlo was a Hungarian-American cinematographer known for his work on films such as "The Warriors," "First Blood," and "Streets of Fire."
  • C. Charles Rackoff
    Charles Rackoff is a Canadian computer scientist known for his influential work in cryptography and computational complexity theory.
  • D. Chris Rosenau
    Chris Rosenau is an American guitarist and composer best known for his intricate, experimental work in projects like Volcano Choir and the duo Collections of Colonies of Bees.
  • E. Bertram Bloch
    Bertram Bloch was a writer whose work served as the source material for the film "Dark Victory."
  • 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_69ca84286fcc81909f6e7fd7a7e862a2 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd4bafa9108190889397614756020d completed April 1, 2026, 4:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69d100c7f3748190bfa4c3a4df8c5d42 completed April 4, 2026, 12:15 p.m.
Created at: March 30, 2026, 7:40 p.m.