Triple
T12315115
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Waihi |
E293579
|
entity |
| Predicate | hasSchool |
P113
|
FINISHED |
| Object |
Waihi College
Waihi College is a co-educational secondary school in Waihi, New Zealand, serving students from early secondary through senior high school levels.
|
E976051
|
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: Waihi College | Statement: [Waihi, hasSchool, Waihi College]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Waihi College Context triple: [Waihi, hasSchool, Waihi College]
-
A.
Aorere College
Aorere College is a co-educational secondary school located in Māngere, South Auckland, New Zealand.
-
B.
Otahuhu College
Otahuhu College is a secondary school located in the suburb of Ōtāhuhu in Auckland, New Zealand.
-
C.
Te Kuiti High School
Te Kuiti High School is a co-educational secondary school serving the rural community of Te Kuiti in New Zealand’s Waikato region.
-
D.
Onehunga High School
Onehunga High School is a co-educational secondary school in the Auckland suburb of Onehunga, New Zealand, known for its diverse student body and strong academic and vocational programs.
-
E.
Whanganui City College
Whanganui City College is a secondary school in Whanganui, New Zealand, providing education for local high school students.
- 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: Waihi College Triple: [Waihi, hasSchool, Waihi College]
Generated description
Waihi College is a co-educational secondary school in Waihi, New Zealand, serving students from early secondary through senior high school levels.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Waihi College Target entity description: Waihi College is a co-educational secondary school in Waihi, New Zealand, serving students from early secondary through senior high school levels.
-
A.
Aorere College
Aorere College is a co-educational secondary school located in Māngere, South Auckland, New Zealand.
-
B.
Otahuhu College
Otahuhu College is a secondary school located in the suburb of Ōtāhuhu in Auckland, New Zealand.
-
C.
Te Kuiti High School
Te Kuiti High School is a co-educational secondary school serving the rural community of Te Kuiti in New Zealand’s Waikato region.
-
D.
Onehunga High School
Onehunga High School is a co-educational secondary school in the Auckland suburb of Onehunga, New Zealand, known for its diverse student body and strong academic and vocational programs.
-
E.
Whanganui City College
Whanganui City College is a secondary school in Whanganui, New Zealand, providing education for local high school students.
- 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_69d6ab6a2b50819082f6aedd32ed608a |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d93f05186481909c024a933b4f6c60 |
completed | April 10, 2026, 6:18 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f61e86d45881909a9a3c09df0b78f1 |
completed | May 2, 2026, 3:55 p.m. |
| NEDg | Description generation | batch_69f622a646c481908164ae5387625bb4 |
completed | May 2, 2026, 4:13 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f623fbb32081909b7daa515eebf75d |
completed | May 2, 2026, 4:19 p.m. |
Created at: April 8, 2026, 9:53 p.m.