Triple

T15576964
Position Surface form Disambiguated ID Type / Status
Subject Marc Spector E374392 entity
Predicate enemy P4567 FINISHED
Object Black Spectre E969255 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: Black Spectre | Statement: [Marc Spector, enemy, Black Spectre]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Black Spectre
Context triple: [Marc Spector, enemy, Black Spectre]
  • A. Black Spectre chosen
    Black Spectre is a recurring Marvel Comics supervillain and nemesis of Moon Knight, typically portrayed as a ruthless, armored vigilante or terrorist driven by a desire for power and chaos.
  • B. The Wraith
    The Wraith is a 1986 cult action-horror film blending supernatural revenge and car-racing elements, starring Charlie Sheen and Nick Cassavetes.
  • C. Schadow
    Schadow is a German surname most notably associated with Johann Gottfried Schadow, an influential neoclassical sculptor of the late 18th and early 19th centuries.
  • D. Black Soulstone
    The Black Soulstone is a powerful and corrupted artifact in the Diablo universe capable of imprisoning and manipulating the souls of the Prime and Lesser Evils.
  • E. Soultaker
    Soultaker is a low-budget 1990 supernatural horror film best known for its cult status and appearance on Mystery Science Theater 3000.
  • 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_69d85ccd575081908909b71a3f3e3a61 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04e22c89081909b1ec0cd36a1ef45 completed April 16, 2026, 2:49 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff4c4978ec8190a57de5d9a2ec6653 completed May 9, 2026, 3:01 p.m.
Created at: April 10, 2026, 4:11 a.m.