Triple

T3056778
Position Surface form Disambiguated ID Type / Status
Subject Midrand E60499 entity
Predicate hasSuburb P747 FINISHED
Object Glen Austin
Glen Austin is a residential and semi-rural suburb located within the Midrand area of Johannesburg, South Africa.
E323444 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: Glen Austin | Statement: [Midrand, hasSuburb, Glen Austin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Glen Austin
Context triple: [Midrand, hasSuburb, Glen Austin]
  • A. Peter Casey
    Peter Casey is an American television producer and writer best known as a co-creator of the acclaimed sitcom "Frasier."
  • B. John Morris
    John Morris is an American voice actor best known for voicing Andy Davis in the Toy Story film series.
  • C. John Morris
    John Morris is a film producer best known for his work on mainstream Hollywood comedies, including the family sequel "Daddy's Home 2."
  • D. Craig Wood
    Craig Wood is a film editor best known for his work on major Hollywood blockbusters, including entries in the Pirates of the Caribbean franchise.
  • E. Retief
    Retief is an Afrikaans surname of French Huguenot origin, notably borne by South African historical figures and athletes.
  • 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: Glen Austin
Triple: [Midrand, hasSuburb, Glen Austin]
Generated description
Glen Austin is a residential and semi-rural suburb located within the Midrand area of Johannesburg, South Africa.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Glen Austin
Target entity description: Glen Austin is a residential and semi-rural suburb located within the Midrand area of Johannesburg, South Africa.
  • A. Peter Casey
    Peter Casey is an American television producer and writer best known as a co-creator of the acclaimed sitcom "Frasier."
  • B. John Morris
    John Morris is an American voice actor best known for voicing Andy Davis in the Toy Story film series.
  • C. John Morris
    John Morris is a film producer best known for his work on mainstream Hollywood comedies, including the family sequel "Daddy's Home 2."
  • D. Craig Wood
    Craig Wood is a film editor best known for his work on major Hollywood blockbusters, including entries in the Pirates of the Caribbean franchise.
  • E. Retief
    Retief is an Afrikaans surname of French Huguenot origin, notably borne by South African historical figures and athletes.
  • 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_69ad8578137c81908259dcb27c7d6d7c completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ad9e13f16c81909e11ed1444c71151 completed March 8, 2026, 4:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69b1ef0671e48190a793f907cc211dd8 completed March 11, 2026, 10:39 p.m.
NEDg Description generation batch_69b1efcf4da08190a9fd5fd88bba0358 completed March 11, 2026, 10:42 p.m.
NED2 Entity disambiguation (via description) batch_69b1f1ce72388190871884c99526057d completed March 11, 2026, 10:50 p.m.
Created at: March 8, 2026, 3:02 p.m.