Triple

T100767
Position Surface form Disambiguated ID Type / Status
Subject Easter Island E2034 entity
Predicate hasWritingSystem P454 FINISHED
Object rongorongo
Rongorongo is an undeciphered system of glyphs from Easter Island, believed to be a unique and possibly independent invention of writing in Polynesia.
E9128 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: rongorongo | Statement: [Easter Island, hasWritingSystem, rongorongo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: rongorongo
Context triple: [Easter Island, hasWritingSystem, rongorongo]
  • A. Kichwa
    Kichwa is a Quechuan indigenous language variety widely spoken by Andean communities in Ecuador and neighboring regions.
  • B. Kalorama
    Kalorama is an affluent, historic residential neighborhood in Northwest Washington, D.C., known for its embassies, stately mansions, and prominent political residents.
  • C. Gori
    Gori is a city in central Georgia best known as the birthplace of Soviet leader Joseph Stalin.
  • D. Namba
    Namba is a major commercial and entertainment district in Osaka, Japan, known for its bustling nightlife, shopping, and iconic neon-lit streets.
  • E. Dededo
    Dededo is a major village and commercial center in northern Guam, known for its large population and role as a key residential and retail hub on the island.
  • 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: rongorongo
Triple: [Easter Island, hasWritingSystem, rongorongo]
Generated description
Rongorongo is an undeciphered system of glyphs from Easter Island, believed to be a unique and possibly independent invention of writing in Polynesia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: rongorongo
Target entity description: Rongorongo is an undeciphered system of glyphs from Easter Island, believed to be a unique and possibly independent invention of writing in Polynesia.
  • A. Kichwa
    Kichwa is a Quechuan indigenous language variety widely spoken by Andean communities in Ecuador and neighboring regions.
  • B. Kalorama
    Kalorama is an affluent, historic residential neighborhood in Northwest Washington, D.C., known for its embassies, stately mansions, and prominent political residents.
  • C. Gori
    Gori is a city in central Georgia best known as the birthplace of Soviet leader Joseph Stalin.
  • D. Namba
    Namba is a major commercial and entertainment district in Osaka, Japan, known for its bustling nightlife, shopping, and iconic neon-lit streets.
  • E. Dededo
    Dededo is a major village and commercial center in northern Guam, known for its large population and role as a key residential and retail hub on the island.
  • 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_69a24e0a5b7c81908d52da08c60dabc4 completed Feb. 28, 2026, 2:08 a.m.
NER Named-entity recognition batch_69a256a7957c8190bf9924eff7572b95 completed Feb. 28, 2026, 2:44 a.m.
NED1 Entity disambiguation (via context triple) batch_69a266ee56548190a781e2d0ea7fac2b completed Feb. 28, 2026, 3:54 a.m.
NEDg Description generation batch_69a2678d1b808190aa9e6451d7945f58 completed Feb. 28, 2026, 3:57 a.m.
NED2 Entity disambiguation (via description) batch_69a26853ed9881909e55192266bfd0b4 completed Feb. 28, 2026, 4 a.m.
Created at: Feb. 28, 2026, 2:12 a.m.