Triple

T19792337
Position Surface form Disambiguated ID Type / Status
Subject Māngere E475444 entity
Predicate hasEducationalInstitution P113 FINISHED
Object Koru School
Koru School is a primary educational institution located in the suburb of Māngere in Auckland, New Zealand.
E1398507 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: Koru School | Statement: [Māngere, hasEducationalInstitution, Koru School]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Koru School
Context triple: [Māngere, hasEducationalInstitution, Koru School]
  • A. Onerahi School
    Onerahi School is a primary school serving the local community of Onerahi in Whangārei, New Zealand.
  • B. Ohaupo School
    Ohaupo School is a primary school serving the rural community of Ohaupo in the Waikato region of New Zealand.
  • C. Matakohe School
    Matakohe School is a small primary school serving the rural community of Matakohe in Northland, New Zealand.
  • D. Ōtaki School
    Ōtaki School is a local primary educational institution serving the community of Ōtaki in New Zealand.
  • E. Aokautere School
    Aokautere School is a primary educational institution serving the local community of Aokautere in New Zealand.
  • 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: Koru School
Triple: [Māngere, hasEducationalInstitution, Koru School]
Generated description
Koru School is a primary educational institution located in the suburb of Māngere in Auckland, New Zealand.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Koru School
Target entity description: Koru School is a primary educational institution located in the suburb of Māngere in Auckland, New Zealand.
  • A. Onerahi School
    Onerahi School is a primary school serving the local community of Onerahi in Whangārei, New Zealand.
  • B. Ohaupo School
    Ohaupo School is a primary school serving the rural community of Ohaupo in the Waikato region of New Zealand.
  • C. Matakohe School
    Matakohe School is a small primary school serving the rural community of Matakohe in Northland, New Zealand.
  • D. Ōtaki School
    Ōtaki School is a local primary educational institution serving the community of Ōtaki in New Zealand.
  • E. Aokautere School
    Aokautere School is a primary educational institution serving the local community of Aokautere in New Zealand.
  • 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_69d8e51b014081908b263e167370529a completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e653c37a3c819080f195d58adaaa7b completed April 20, 2026, 4:26 p.m.
NED1 Entity disambiguation (via context triple) batch_6a07d42c1a0481909a505a37aa92ad5e completed May 16, 2026, 2:19 a.m.
NEDg Description generation batch_6a07d4e943b081909f98c72683d62e62 completed May 16, 2026, 2:22 a.m.
NED2 Entity disambiguation (via description) batch_6a07d5bc8e748190a4f97e6b23e56edd completed May 16, 2026, 2:26 a.m.
Created at: April 10, 2026, 1:49 p.m.