Triple

T2302035
Position Surface form Disambiguated ID Type / Status
Subject Pollsmoor Prison E51754 entity
Predicate locatedIn P40 FINISHED
Object Tokai
Tokai is a suburb in Cape Town, South Africa, known for its residential areas, green spaces, and proximity to the Constantiaberg mountains.
 E305398 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: Tokai | Statement: [Pollsmoor Prison, locatedIn, Tokai]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Tokai
Context triple: [Pollsmoor Prison, locatedIn, Tokai]
  • A. Tenri
    Tenri is a small city in Japan known as the headquarters of the Tenrikyo religion and for its rich archaeological and cultural heritage.
  • B. Shinano
    Shinano was a Japanese World War II aircraft carrier, originally laid down as a Yamato-class battleship and notable for being the largest carrier ever sunk in combat.
  • C. Settsu
    Settsu is a city in Osaka Prefecture, Japan, known as part of the Osaka metropolitan area.
  • D. Izumo
    Izumo is a coastal city in Japan’s Shimane Prefecture, best known for the ancient Shinto shrine Izumo Taisha, one of the country’s most important religious sites.
  • E. Kamiyama
    Kamiyama is a Japanese surname borne by various individuals, including artists, athletes, and public figures.
  • 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: Tokai
Triple: [Pollsmoor Prison, locatedIn, Tokai]
Generated description
Tokai is a suburb in Cape Town, South Africa, known for its residential areas, green spaces, and proximity to the Constantiaberg mountains.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Tokai
Target entity description: Tokai is a suburb in Cape Town, South Africa, known for its residential areas, green spaces, and proximity to the Constantiaberg mountains.
  • A. Tenri
    Tenri is a small city in Japan known as the headquarters of the Tenrikyo religion and for its rich archaeological and cultural heritage.
  • B. Shinano
    Shinano was a Japanese World War II aircraft carrier, originally laid down as a Yamato-class battleship and notable for being the largest carrier ever sunk in combat.
  • C. Settsu
    Settsu is a city in Osaka Prefecture, Japan, known as part of the Osaka metropolitan area.
  • D. Izumo
    Izumo is a coastal city in Japan’s Shimane Prefecture, best known for the ancient Shinto shrine Izumo Taisha, one of the country’s most important religious sites.
  • E. Kamiyama
    Kamiyama is a Japanese surname borne by various individuals, including artists, athletes, and public figures.
  • 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_69a88b0a9f248190bcff941463d8f65a completed March 4, 2026, 7:42 p.m.
NER Named-entity recognition batch_69abc5ef51948190ae828d8ee02feb75 completed March 7, 2026, 6:30 a.m.
NED1 Entity disambiguation (via context triple) batch_69b01d0915148190b77b8a30fa3f796d completed March 10, 2026, 1:30 p.m.
NEDg Description generation batch_69b01def4f408190a0fcdba125b642bc completed March 10, 2026, 1:34 p.m.
NED2 Entity disambiguation (via description) batch_69b01e75d3c4819097fd86902eccd8c4 completed March 10, 2026, 1:36 p.m.
Created at: March 4, 2026, 7:49 p.m.