Triple

T3714002
Position Surface form Disambiguated ID Type / Status
Subject Alexander Archipelago E81481 entity
Predicate hasCity P316 FINISHED
Object Hydaburg
Hydaburg is a small city on Prince of Wales Island in Alaska known as a central community for the Haida people and their culture.
E381394 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: Hydaburg | Statement: [Alexander Archipelago, hasCity, Hydaburg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hydaburg
Context triple: [Alexander Archipelago, hasCity, Hydaburg]
  • A. Taku City
    Taku City is a municipality in Saga Prefecture, Japan, known for its historic sites and traditional Japanese townscape.
  • B. Sitka
    Sitka is a historic coastal city in southeastern Alaska known for its Tlingit and Russian heritage, scenic island setting, and abundant wildlife.
  • C. Savoonga
    Savoonga is a remote Alaska Native village on St. Lawrence Island in the Bering Sea, known for its Siberian Yupik culture and subsistence hunting lifestyle.
  • D. Port Lions
    Port Lions is a small Alutiiq community and fishing village located on Kodiak Island in Alaska.
  • E. Bilibino
    Bilibino is a small town in Russia’s Far East best known for hosting one of the world’s northernmost nuclear power plants.
  • 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: Hydaburg
Triple: [Alexander Archipelago, hasCity, Hydaburg]
Generated description
Hydaburg is a small city on Prince of Wales Island in Alaska known as a central community for the Haida people and their culture.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Hydaburg
Target entity description: Hydaburg is a small city on Prince of Wales Island in Alaska known as a central community for the Haida people and their culture.
  • A. Taku City
    Taku City is a municipality in Saga Prefecture, Japan, known for its historic sites and traditional Japanese townscape.
  • B. Sitka
    Sitka is a historic coastal city in southeastern Alaska known for its Tlingit and Russian heritage, scenic island setting, and abundant wildlife.
  • C. Savoonga
    Savoonga is a remote Alaska Native village on St. Lawrence Island in the Bering Sea, known for its Siberian Yupik culture and subsistence hunting lifestyle.
  • D. Port Lions
    Port Lions is a small Alutiiq community and fishing village located on Kodiak Island in Alaska.
  • E. Bilibino
    Bilibino is a small town in Russia’s Far East best known for hosting one of the world’s northernmost nuclear power plants.
  • 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_69ad8b1a81588190b3f27a5483bb610e completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69adc9ccfad081908730ed15c6f87ce2 completed March 8, 2026, 7:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4ce0c3320819092ca5dd0694e167f completed March 14, 2026, 2:55 a.m.
NEDg Description generation batch_69b4ceef46cc819096e0d824153d1544 completed March 14, 2026, 2:58 a.m.
NED2 Entity disambiguation (via description) batch_69b4cf6c4e5c8190bee35fc33d707823 completed March 14, 2026, 3:01 a.m.
Created at: March 8, 2026, 3:33 p.m.