Triple

T15710885
Position Surface form Disambiguated ID Type / Status
Subject Michael Tolkin E380832 entity
Predicate notableWork P4 FINISHED
Object Under Radar
Under Radar is a film written and directed by American screenwriter and filmmaker Michael Tolkin.
 E1172998 NE FINISHED

How this triple was built (4 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: Under Radar | Statement: [Michael Tolkin, notableWork, Under Radar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Under Radar
Context triple: [Michael Tolkin, notableWork, Under Radar]
  • A. Underneath
    "Underneath" is a song by American pop-rock band Hanson, known for showcasing their more mature sound and songwriting beyond their early teen-pop success.
  • B. Undercovers
    Undercovers is an American action-spy television series created by J.J. Abrams that follows a married couple who are reactivated as CIA agents.
  • C. Out from Under
    "Out from Under" is a song by the American pop group Circus, featured as one of the tracks on their music releases.
  • D. Beneath the Surface
    "Beneath the Surface" is GZA's 1999 follow-up studio album that continues his intricate, metaphor-rich lyricism over dark, atmospheric production within the Wu-Tang Clan universe.
  • E. Keep Under Cover
    "Keep Under Cover" is a song by Paul McCartney from his 1983 album "Pipes of Peace," noted for its polished pop production and melodic hooks.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Under Radar
Triple: [Michael Tolkin, notableWork, Under Radar]
Generated description
Under Radar is a film written and directed by American screenwriter and filmmaker Michael Tolkin.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Under Radar
Target entity description: Under Radar is a film written and directed by American screenwriter and filmmaker Michael Tolkin.
  • A. Underneath
    "Underneath" is a song by American pop-rock band Hanson, known for showcasing their more mature sound and songwriting beyond their early teen-pop success.
  • B. Undercovers
    Undercovers is an American action-spy television series created by J.J. Abrams that follows a married couple who are reactivated as CIA agents.
  • C. Out from Under
    "Out from Under" is a song by the American pop group Circus, featured as one of the tracks on their music releases.
  • D. Beneath the Surface
    "Beneath the Surface" is GZA's 1999 follow-up studio album that continues his intricate, metaphor-rich lyricism over dark, atmospheric production within the Wu-Tang Clan universe.
  • E. Keep Under Cover
    "Keep Under Cover" is a song by Paul McCartney from his 1983 album "Pipes of Peace," noted for its polished pop production and melodic hooks.
  • F. None of above. chosen

Provenance (5 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_69d86d9bf930819082b30cf6d169297c completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e04f8f5d6081908243fa59b46b7c76 completed April 16, 2026, 2:55 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff757d74b481909c8332a09ae36b4f completed May 9, 2026, 5:57 p.m.
NEDg Description generation batch_69ff762c0c548190a80392e1e83f68cc completed May 9, 2026, 6 p.m.
NED2 Entity disambiguation (via description) batch_69ff76fbcd188190b431bf277304aeea completed May 9, 2026, 6:03 p.m.
Created at: April 10, 2026, 4:45 a.m.