Triple

T12971538
Position Surface form Disambiguated ID Type / Status
Subject Tanimbar Islands E321408 entity
Predicate hasIsland P970 FINISHED
Object Fordata
Fordata is one of the islands in Indonesia’s Tanimbar archipelago, located in the Maluku province.
E1013585 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: Fordata | Statement: [Tanimbar Islands, hasIsland, Fordata]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fordata
Context triple: [Tanimbar Islands, hasIsland, Fordata]
  • A. Daatu
    Daatu is a Kannada novel by S. L. Bhyrappa that explores complex social and caste dynamics in Indian society.
  • B. Adatan
    Adatan is a neighborhood and urban district within Abeokuta South in Ogun State, southwestern Nigeria.
  • C. Nentego
    Nentego is the autonym of the Nanticoke people, an Indigenous group historically located in the Mid-Atlantic region of what is now the United States.
  • D. Argotec
    Argotec is an Italian aerospace engineering company specializing in the design and development of small satellites and space systems for scientific and commercial missions.
  • E. Founex
    Founex is a small Swiss municipality on Lake Geneva in the canton of Vaud, known for its residential character and proximity to Geneva.
  • 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: Fordata
Triple: [Tanimbar Islands, hasIsland, Fordata]
Generated description
Fordata is one of the islands in Indonesia’s Tanimbar archipelago, located in the Maluku province.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Fordata
Target entity description: Fordata is one of the islands in Indonesia’s Tanimbar archipelago, located in the Maluku province.
  • A. Daatu
    Daatu is a Kannada novel by S. L. Bhyrappa that explores complex social and caste dynamics in Indian society.
  • B. Adatan
    Adatan is a neighborhood and urban district within Abeokuta South in Ogun State, southwestern Nigeria.
  • C. Nentego
    Nentego is the autonym of the Nanticoke people, an Indigenous group historically located in the Mid-Atlantic region of what is now the United States.
  • D. Argotec
    Argotec is an Italian aerospace engineering company specializing in the design and development of small satellites and space systems for scientific and commercial missions.
  • E. Founex
    Founex is a small Swiss municipality on Lake Geneva in the canton of Vaud, known for its residential character and proximity to Geneva.
  • 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_69d80763bd6c819094437da5b20b01d2 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69d97e418d548190be1c73db76cb3aa8 completed April 10, 2026, 10:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6b8ea91f08190b1daf6d05621acf9 completed May 3, 2026, 2:54 a.m.
NEDg Description generation batch_69f6b9a1ca54819085da2ca592bf5219 completed May 3, 2026, 2:57 a.m.
NED2 Entity disambiguation (via description) batch_69f6bb03d8d88190930edd0f49fec8aa completed May 3, 2026, 3:03 a.m.
Created at: April 9, 2026, 8:36 p.m.