Triple

T16086493
Position Surface form Disambiguated ID Type / Status
Subject River Song E390240 entity
Predicate notableEpisode P2757 FINISHED
Object "Flesh and Stone" E390237 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: "Flesh and Stone" | Statement: [River Song, notableEpisode, "Flesh and Stone"]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: "Flesh and Stone"
Context triple: [River Song, notableEpisode, "Flesh and Stone"]
  • A. Flesh and Stone chosen
    "Flesh and Stone" is a 2010 Doctor Who television episode featuring the Eleventh Doctor, continuing the Weeping Angels storyline begun in "The Time of Angels."
  • B. Made of Stone
    "Made of Stone" is a 1989 indie rock song by The Stone Roses, regarded as one of their signature tracks and a key anthem of the Madchester era.
  • C. Stone to the Bone
    "Stone to the Bone" is a funk track by James Brown featured on his influential 1973 album *The Payback*.
  • D. The Man Who Turned to Stone
    "The Man Who Turned to Stone" is a work of fiction by Australian writer Charlotte Austin, likely a short story or novella that showcases her contemporary literary style.
  • E. "To Turn the Stone"
    "To Turn the Stone" is a pop song performed by Norwegian singer Frida, best known as a member of the group ABBA.
  • 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_69d87f198bc48190a8b7e53ca15b7ead completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e1844f95508190a06dad0ccc9b6191 completed April 17, 2026, 12:52 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffeb934b448190a486401ac6c01065 completed May 10, 2026, 2:21 a.m.
Created at: April 10, 2026, 4:59 a.m.