Triple

T22534485
Position Surface form Disambiguated ID Type / Status
Subject Living Things E557120 entity
Predicate track P17929 FINISHED
Object Castle of Glass 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: Castle of Glass | Statement: [Living Things, track, Castle of Glass]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Castle of Glass
Context triple: [Living Things, track, Castle of Glass]
  • A. Castle of Glass chosen
    "Castle of Glass" is a song by the American rock band Linkin Park, known for its electronic rock sound and introspective lyrics.
  • B. Tower of Glass
    Tower of Glass is a 1970 science fiction novel by Robert Silverberg that explores themes of artificial intelligence, class hierarchy, and the ethics of creating sentient beings.
  • C. La Reine de l’ombre
    La Reine de l’ombre is a dramatic work by French playwright Marcelle Maurette, best known for its psychologically intense portrayal of a complex female protagonist.
  • D. Shard of Glass
    Shard of Glass is a landmark skyscraper in London known for its distinctive glass-clad, shard-like design and status as one of the tallest buildings in the United Kingdom.
  • E. City of Glass
    City of Glass is a postmodern detective novel by Paul Auster that blends mystery, metafiction, and philosophical inquiry into identity and language.
  • 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_69e11e57483c8190b0887c4f8ff26446 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15ed952f48190b63225e7de131679 completed April 29, 2026, 1:28 a.m.
Created at: April 16, 2026, 8:51 p.m.