Triple

T7678674
Position Surface form Disambiguated ID Type / Status
Subject Bastia E173930 entity
Predicate hasPart P35 FINISHED
Object Terra Nova
Terra Nova is a neighborhood or district within the Corsican city of Bastia, France.
E681400 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: Terra Nova | Statement: [Bastia, hasPart, Terra Nova]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Terra Nova
Context triple: [Bastia, hasPart, Terra Nova]
  • A. Terra Nova
    Terra Nova is a major offshore oil field and production facility located on the Grand Banks off the coast of Newfoundland and Labrador, Canada.
  • B. Terra Nova
    Terra Nova was a British whaling and exploration ship best known for carrying Robert Falcon Scott’s ill-fated Terra Nova Expedition to Antarctica in the early 20th century.
  • C. Terra Nova
    Terra Nova is a science fiction television series set in a dystopian future where humans travel back to prehistoric Earth to save civilization.
  • D. Ice Land
    Ice Land is a frigid, snow- and ice-themed world in Super Mario Bros. 3 known for its slippery terrain and cold-weather enemies.
  • E. Les Machines de l’Île
    Les Machines de l’Île is a large-scale artistic and cultural project in Nantes featuring fantastical mechanical creatures and interactive machines inspired by Jules Verne and Leonardo da Vinci.
  • 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: Terra Nova
Triple: [Bastia, hasPart, Terra Nova]
Generated description
Terra Nova is a neighborhood or district within the Corsican city of Bastia, France.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Terra Nova
Target entity description: Terra Nova is a neighborhood or district within the Corsican city of Bastia, France.
  • A. Terra Nova
    Terra Nova is a major offshore oil field and production facility located on the Grand Banks off the coast of Newfoundland and Labrador, Canada.
  • B. Terra Nova
    Terra Nova is a science fiction television series set in a dystopian future where humans travel back to prehistoric Earth to save civilization.
  • C. Terra Nova
    Terra Nova was a British whaling and exploration ship best known for carrying Robert Falcon Scott’s ill-fated Terra Nova Expedition to Antarctica in the early 20th century.
  • D. Ice Land
    Ice Land is a frigid, snow- and ice-themed world in Super Mario Bros. 3 known for its slippery terrain and cold-weather enemies.
  • E. Les Machines de l’Île
    Les Machines de l’Île is a large-scale artistic and cultural project in Nantes featuring fantastical mechanical creatures and interactive machines inspired by Jules Verne and Leonardo da Vinci.
  • 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_69c6995703e0819081de77361b602e78 completed March 27, 2026, 2:51 p.m.
NER Named-entity recognition batch_69c701fd18d88190888144a7d0f228d9 completed March 27, 2026, 10:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8a248750481908f0de08aee78c9ba completed March 29, 2026, 3:53 a.m.
NEDg Description generation batch_69c8a2fd5a348190a952f6cc3e622474 completed March 29, 2026, 3:56 a.m.
NED2 Entity disambiguation (via description) batch_69c8a3a570948190ba733c3c858d4bfd completed March 29, 2026, 3:59 a.m.
Created at: March 27, 2026, 4:01 p.m.