Triple

T7420878
Position Surface form Disambiguated ID Type / Status
Subject Rob Van Dam E171241 entity
Predicate trainedBy P3665 FINISHED
Object Sabu
Sabu is a pioneering hardcore professional wrestler best known for his extreme, high-risk style and influential run in ECW.
 E662782 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: Sabu | Statement: [Rob Van Dam, trainedBy, Sabu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sabu
Context triple: [Rob Van Dam, trainedBy, Sabu]
  • A. Sabu
    Sabu is an alternative name for the Shabo language, a little-documented and possibly language-isolate tongue spoken by a small community in southwestern Ethiopia.
  • B. Ganja
    Ganja is one of Azerbaijan’s largest and oldest cities, known as a historic cultural and economic center in the South Caucasus.
  • C. Sahl Hasheesh
    Sahl Hasheesh is a modern Red Sea coastal resort town in Egypt known for its luxury hotels, beaches, and diving and snorkeling sites.
  • D. Substiane
    Substiane is a La Roche-Posay skincare line formulated to address loss of firmness, density, and comfort in mature or aging skin.
  • E. Droguinhas
    "Droguinhas" is an experimental series of knotted and twisted paper sculptures by Brazilian artist Mira Schendel that explores language, materiality, and the physical form of thought.
  • 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: Sabu
Triple: [Rob Van Dam, trainedBy, Sabu]
Generated description
Sabu is a pioneering hardcore professional wrestler best known for his extreme, high-risk style and influential run in ECW.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sabu
Target entity description: Sabu is a pioneering hardcore professional wrestler best known for his extreme, high-risk style and influential run in ECW.
  • A. Sabu
    Sabu is an alternative name for the Shabo language, a little-documented and possibly language-isolate tongue spoken by a small community in southwestern Ethiopia.
  • B. Ganja
    Ganja is one of Azerbaijan’s largest and oldest cities, known as a historic cultural and economic center in the South Caucasus.
  • C. Sahl Hasheesh
    Sahl Hasheesh is a modern Red Sea coastal resort town in Egypt known for its luxury hotels, beaches, and diving and snorkeling sites.
  • D. Substiane
    Substiane is a La Roche-Posay skincare line formulated to address loss of firmness, density, and comfort in mature or aging skin.
  • E. Droguinhas
    "Droguinhas" is an experimental series of knotted and twisted paper sculptures by Brazilian artist Mira Schendel that explores language, materiality, and the physical form of thought.
  • 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_69c68a625d048190af70eb8b63bec5a0 completed March 27, 2026, 1:47 p.m.
NER Named-entity recognition batch_69c6f2ebc520819087cfc2eb9dda0e17 completed March 27, 2026, 9:13 p.m.
NED1 Entity disambiguation (via context triple) batch_69c81ef7fc808190a564ab4d9d97ab37 completed March 28, 2026, 6:33 p.m.
NEDg Description generation batch_69c81f9b565881909bebcc3112037f52 completed March 28, 2026, 6:36 p.m.
NED2 Entity disambiguation (via description) batch_69c8207912f4819086e99ed441bee805 completed March 28, 2026, 6:39 p.m.
Created at: March 27, 2026, 3:11 p.m.