Triple

T9997843
Position Surface form Disambiguated ID Type / Status
Subject Karel Roden E197247 entity
Predicate notableWork P4 FINISHED
Object T.M.A.
T.M.A. is a Czech horror film in which a man returns to his childhood home in a remote village and confronts dark supernatural forces tied to his past.
 E833714 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: T.M.A. | Statement: [Karel Roden, notableWork, T.M.A.]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: T.M.A.
Context triple: [Karel Roden, notableWork, T.M.A.]
  • A. T.O.M.
    T.O.M. is the robotic host and mascot of Cartoon Network’s Toonami programming block, known for introducing shows and guiding viewers through the lineup in a futuristic spaceship setting.
  • B. T.O.T.S.
    T.O.T.S. is an animated Disney Junior series that follows two delivery birds who transport baby animals to their families while learning lessons about friendship and responsibility.
  • C. TAM
    TAM is the standard abbreviation used for the Tampa Tarpons, a Minor League Baseball team based in Tampa, Florida.
  • D. TAM
    TAM is the former brand name and airline code of LATAM Airlines Brasil, one of Brazil’s largest commercial airlines.
  • E. TAM
    TAM is a prominent annual conference focused on science, skepticism, and critical thinking, originally organized by the James Randi Educational Foundation.
  • 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: T.M.A.
Triple: [Karel Roden, notableWork, T.M.A.]
Generated description
T.M.A. is a Czech horror film in which a man returns to his childhood home in a remote village and confronts dark supernatural forces tied to his past.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: T.M.A.
Target entity description: T.M.A. is a Czech horror film in which a man returns to his childhood home in a remote village and confronts dark supernatural forces tied to his past.
  • A. T.O.M.
    T.O.M. is the robotic host and mascot of Cartoon Network’s Toonami programming block, known for introducing shows and guiding viewers through the lineup in a futuristic spaceship setting.
  • B. T.O.T.S.
    T.O.T.S. is an animated Disney Junior series that follows two delivery birds who transport baby animals to their families while learning lessons about friendship and responsibility.
  • C. TAM
    TAM is the standard abbreviation used for the Tampa Tarpons, a Minor League Baseball team based in Tampa, Florida.
  • D. TAM
    TAM is the former brand name and airline code of LATAM Airlines Brasil, one of Brazil’s largest commercial airlines.
  • E. TAM
    TAM is a prominent annual conference focused on science, skepticism, and critical thinking, originally organized by the James Randi Educational Foundation.
  • 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_69ca82f3b61c81908ecc2c1c96dbc2e4 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cdcc8aa1a881909879a694496f11a5 completed April 2, 2026, 1:55 a.m.
NED1 Entity disambiguation (via context triple) batch_69d258439fe88190b17da69f542ecf61 completed April 5, 2026, 12:40 p.m.
NEDg Description generation batch_69d259701e488190b288c9f523a1ec87 completed April 5, 2026, 12:45 p.m.
NED2 Entity disambiguation (via description) batch_69d259da25e081909ac184f4fa80c57e completed April 5, 2026, 12:47 p.m.
Created at: March 30, 2026, 8:51 p.m.