Triple

T16314902
Position Surface form Disambiguated ID Type / Status
Subject Otago Peninsula E396148 entity
Predicate contains P35 FINISHED
Object Otakou
Otakou is a small coastal settlement and historic Māori kāinga on the Otago Peninsula in New Zealand, significant as an early center of Māori–European interaction and Ngāi Tahu history.
E1205266 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: Otakou | Statement: [Otago Peninsula, contains, Otakou]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Otakou
Context triple: [Otago Peninsula, contains, Otakou]
  • A. Otuokpoti
    Otuokpoti is a town located in the Ogbia area of Bayelsa State in Nigeria.
  • B. Okoto
    Okoto is one of Bulgaria’s glacial Seven Rila Lakes, known for its deep, eye-shaped basin set high in the Rila Mountains.
  • C. Ōtoku
    Ōtoku was a Japanese era name (nengō) of the late 11th century, used during the reign of Emperor Shirakawa.
  • D. Obanliku
    Obanliku is a local government area in southeastern Nigeria known for its scenic highland landscapes and cool climate within Cross River State.
  • E. Ohoka
    Ohoka is a small rural township in New Zealand’s Canterbury region, known for its lifestyle properties and proximity to Christchurch.
  • 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: Otakou
Triple: [Otago Peninsula, contains, Otakou]
Generated description
Otakou is a small coastal settlement and historic Māori kāinga on the Otago Peninsula in New Zealand, significant as an early center of Māori–European interaction and Ngāi Tahu history.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Otakou
Target entity description: Otakou is a small coastal settlement and historic Māori kāinga on the Otago Peninsula in New Zealand, significant as an early center of Māori–European interaction and Ngāi Tahu history.
  • A. Otuokpoti
    Otuokpoti is a town located in the Ogbia area of Bayelsa State in Nigeria.
  • B. Okoto
    Okoto is one of Bulgaria’s glacial Seven Rila Lakes, known for its deep, eye-shaped basin set high in the Rila Mountains.
  • C. Ōtoku
    Ōtoku was a Japanese era name (nengō) of the late 11th century, used during the reign of Emperor Shirakawa.
  • D. Obanliku
    Obanliku is a local government area in southeastern Nigeria known for its scenic highland landscapes and cool climate within Cross River State.
  • E. Ohoka
    Ohoka is a small rural township in New Zealand’s Canterbury region, known for its lifestyle properties and proximity to Christchurch.
  • 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_69d87f255b788190a400eba031dd85d8 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e288de57cc81908cec93309347c385 completed April 17, 2026, 7:24 p.m.
NED1 Entity disambiguation (via context triple) batch_6a001fa88e8c8190b0423b60389896dc completed May 10, 2026, 6:03 a.m.
NEDg Description generation batch_6a002067aa708190bc2583c95ab133a4 completed May 10, 2026, 6:06 a.m.
NED2 Entity disambiguation (via description) batch_6a00214a2a908190a11388a63de1f7af completed May 10, 2026, 6:10 a.m.
Created at: April 10, 2026, 5:06 a.m.