Triple

T1983339
Position Surface form Disambiguated ID Type / Status
Subject Saint-Étienne E43079 entity
Predicate hasRiver P165 FINISHED
Object Furan
Furan is a river in central France that flows through the city of Saint-Étienne before joining the Loire.
E221328 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: Furan | Statement: [Saint-Étienne, hasRiver, Furan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Furan
Context triple: [Saint-Étienne, hasRiver, Furan]
  • A. Corachol
    Corachol is a subfamily of Uto-Aztecan languages that includes closely related indigenous languages spoken in western Mexico.
  • B. THF
    THF is the former Berlin Tempelhof Airport, a historically significant airfield known for its role in the Berlin Airlift and its later conversion into a vast urban park.
  • C. Fremulon
    Fremulon is a television production company founded by Michael Schur, best known for producing acclaimed comedy series such as Brooklyn Nine-Nine.
  • D. Feigl
    Feigl is a German-language surname borne by various notable individuals, including philosophers, scientists, and artists.
  • E. Tykocin
    Tykocin is a historic town in northeastern Poland known for its well-preserved Jewish heritage, baroque architecture, and role in Polish royal and noble history.
  • 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: Furan
Triple: [Saint-Étienne, hasRiver, Furan]
Generated description
Furan is a river in central France that flows through the city of Saint-Étienne before joining the Loire.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Furan
Target entity description: Furan is a river in central France that flows through the city of Saint-Étienne before joining the Loire.
  • A. Corachol
    Corachol is a subfamily of Uto-Aztecan languages that includes closely related indigenous languages spoken in western Mexico.
  • B. THF
    THF is the former Berlin Tempelhof Airport, a historically significant airfield known for its role in the Berlin Airlift and its later conversion into a vast urban park.
  • C. Fremulon
    Fremulon is a television production company founded by Michael Schur, best known for producing acclaimed comedy series such as Brooklyn Nine-Nine.
  • D. Feigl
    Feigl is a German-language surname borne by various notable individuals, including philosophers, scientists, and artists.
  • E. Tykocin
    Tykocin is a historic town in northeastern Poland known for its well-preserved Jewish heritage, baroque architecture, and role in Polish royal and noble history.
  • 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_69a88713ddc88190a969715658ebe7a8 completed March 4, 2026, 7:25 p.m.
NER Named-entity recognition batch_69abb820815481908aac6d89b437225b completed March 7, 2026, 5:31 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae032e1f648190acb502b9f82fe8c2 completed March 8, 2026, 11:15 p.m.
NEDg Description generation batch_69ae03b52ed08190a8c8fb8f81073bb3 completed March 8, 2026, 11:18 p.m.
NED2 Entity disambiguation (via description) batch_69ae0433b90c81909af348d9a3dcdbec completed March 8, 2026, 11:20 p.m.
Created at: March 4, 2026, 7:37 p.m.