Triple
T3174011
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Geelong Grammar School |
E66418
|
entity |
| Predicate | city |
P40
|
FINISHED |
| Object |
Corio
Corio is a residential and industrial suburb in the northern part of Geelong, Victoria, Australia.
|
E333115
|
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: Corio | Statement: [Geelong Grammar School, city, Corio]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Corio Context triple: [Geelong Grammar School, city, Corio]
-
A.
Caloundra
Caloundra is a coastal town at the southern end of Queensland’s Sunshine Coast, known for its family-friendly beaches and relaxed holiday atmosphere.
-
B.
Nayland
Nayland is a small village and civil parish in the county of Suffolk in eastern England, known for its historic buildings and rural setting.
-
C.
Nadi–Auckland
Nadi–Auckland is an international flight route connecting Nadi, Fiji with Auckland, New Zealand.
-
D.
Rangiora
Rangiora is a large rural service town in the Waimakariri District of New Zealand’s South Island, known as a residential and commercial hub for the surrounding agricultural region.
-
E.
Dusky Sound
Dusky Sound is a remote, rugged fiord on the southwest coast of New Zealand’s South Island, renowned for its dramatic scenery, rich marine life, and historical significance to early European explorers.
- 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: Corio Triple: [Geelong Grammar School, city, Corio]
Generated description
Corio is a residential and industrial suburb in the northern part of Geelong, Victoria, Australia.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Corio Target entity description: Corio is a residential and industrial suburb in the northern part of Geelong, Victoria, Australia.
-
A.
Caloundra
Caloundra is a coastal town at the southern end of Queensland’s Sunshine Coast, known for its family-friendly beaches and relaxed holiday atmosphere.
-
B.
Nayland
Nayland is a small village and civil parish in the county of Suffolk in eastern England, known for its historic buildings and rural setting.
-
C.
Nadi–Auckland
Nadi–Auckland is an international flight route connecting Nadi, Fiji with Auckland, New Zealand.
-
D.
Rangiora
Rangiora is a large rural service town in the Waimakariri District of New Zealand’s South Island, known as a residential and commercial hub for the surrounding agricultural region.
-
E.
Dusky Sound
Dusky Sound is a remote, rugged fiord on the southwest coast of New Zealand’s South Island, renowned for its dramatic scenery, rich marine life, and historical significance to early European explorers.
- 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_69ad8586a34c8190944c63ec11a8de1a |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada670c800819098937783e2b05c7a |
completed | March 8, 2026, 4:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b235edf7708190b79605a05baf1711 |
completed | March 12, 2026, 3:41 a.m. |
| NEDg | Description generation | batch_69b236e61ae88190a76b942c6cddff41 |
completed | March 12, 2026, 3:45 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b23770ed4c8190b5d929cc95a286a0 |
completed | March 12, 2026, 3:48 a.m. |
Created at: March 8, 2026, 3:06 p.m.