Triple

T3362585
Position Surface form Disambiguated ID Type / Status
Subject Tom Savini E70757 entity
Predicate actedIn P1668 FINISHED
Object Dawn of the Dead E351254 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: Dawn of the Dead | Statement: [Tom Savini, actedIn, Dawn of the Dead]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dawn of the Dead
Context triple: [Tom Savini, actedIn, Dawn of the Dead]
  • A. Dawn of the Dead chosen
    Dawn of the Dead is a landmark 1978 horror film directed by George A. Romero that helped define the modern zombie genre with its graphic gore, social satire, and influential special effects.
  • B. Zombie
    A Zombie in Minecraft is a common hostile undead mob that attacks players and villagers, often spawning in dark areas and burning in sunlight.
  • C. Zombies
    Zombies is a popular cooperative survival-horror game mode featuring waves of undead enemies, best known from its inclusion in Treyarch’s Call of Duty titles.
  • D. Zombieland
    Zombieland is a 2009 horror-comedy film about a group of survivors navigating a zombie apocalypse with a mix of humor, gore, and quirky survival rules.
  • E. World War Z
    World War Z is a 2013 apocalyptic action-horror film starring Brad Pitt that depicts a global zombie pandemic and humanity’s desperate efforts to survive.
  • 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_69ad85a660c48190998489309a3b4869 completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb26a5a508190948932769de0dbb3 completed March 8, 2026, 5:31 p.m.
NED1 Entity disambiguation (via context triple) batch_69b34bbbc3a48190bc17572ba3136948 completed March 12, 2026, 11:26 p.m.
Created at: March 8, 2026, 3:13 p.m.