Triple

T17912176
Position Surface form Disambiguated ID Type / Status
Subject Alan Scott E447840 entity
Predicate son P25213 FINISHED
Object Obsidian NE NERFINISHED

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: Obsidian | Statement: [Alan Scott, son, Obsidian]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Obsidian
Context triple: [Alan Scott, son, Obsidian]
  • A. Obsidian
    Obsidian is a dark, nearly black color variant commonly used as a sleek, premium finish for electronic devices such as smartphones.
  • B. Obsidian chosen
    Obsidian is a DC Comics superhero, the son of the original Green Lantern Alan Scott, known for his shadow-based powers and complex, often dark storylines.
  • C. Obsidian
    Obsidian is a special episode of the animated series Adventure Time: Distant Lands that focuses on Marceline the Vampire Queen and Princess Bubblegum revisiting their past and confronting an old threat.
  • D. Onyx
    Onyx is a hardcore hip hop group from Queens, New York, known for its aggressive style and influential 1990s releases.
  • E. Onyx
    Onyx is a small unincorporated community in Kern County, California, located in the southern Sierra Nevada near Lake Isabella.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8b9f6d394819082a6d69fd1e23d2f completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e49ea0ea008190b54a999e0704fb67 completed April 19, 2026, 9:21 a.m.
Created at: April 10, 2026, 10:19 a.m.