Triple

T15899909
Position Surface form Disambiguated ID Type / Status
Subject Puerto Francisco de Orellana E385556 entity
Predicate roadConnectedTo P11435 FINISHED
Object Tena E386364 NE FINISHED

How this triple was built (2 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: Tena | Statement: [Puerto Francisco de Orellana, roadConnectedTo, Tena]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tena
Context triple: [Puerto Francisco de Orellana, roadConnectedTo, Tena]
  • A. Tena chosen
    Tena is a small city in Ecuador’s Amazon region known as a gateway for jungle tourism and whitewater rafting.
  • B. Tena
    Tena is a municipality in the Tequendama Province of the Cundinamarca Department in central Colombia, known for its rural landscapes and proximity to Bogotá.
  • C. Teià
    Teià is a small coastal municipality in Catalonia, Spain, situated in the Maresme comarca near Barcelona.
  • D. Bisa
    Bisa is a Gur (Voltaic) language spoken primarily in parts of Burkina Faso and neighboring West African countries.
  • E. Yato
    Yato is a small village on Pukapuka Atoll in the Cook Islands, known for its traditional Polynesian community and remote Pacific island setting.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d86da5b800819083a31be937d738b0 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1563cd2f081909404d724ecc8785a completed April 16, 2026, 9:35 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffb04f3ea08190b5581768770677e8 completed May 9, 2026, 10:08 p.m.
Created at: April 10, 2026, 4:51 a.m.