Triple

T5540264
Position Surface form Disambiguated ID Type / Status
Subject Roman Jakobson E145270 entity
Predicate coAuthor P398 FINISHED
Object Gunnar Fant
Gunnar Fant was a pioneering Swedish speech scientist and phonetician renowned for his foundational work on the acoustic theory of speech production.
E530432 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: Gunnar Fant | Statement: [Roman Jakobson, coAuthor, Gunnar Fant]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gunnar Fant
Context triple: [Roman Jakobson, coAuthor, Gunnar Fant]
  • A. Gunnar Cauthery
    Gunnar Cauthery is an actor best known for his role in the television series "Mars."
  • B. Gunnar
    Gunnar is a masculine given name of Old Norse origin, commonly used in Scandinavian countries and associated with warriors or bold fighters.
  • C. Ulf Danielsson
    Ulf Danielsson is a Swedish theoretical physicist and cosmologist known for his work on string theory and the fundamental nature of the universe.
  • D. Thorolf Rafto
    Thorolf Rafto was a Norwegian human rights advocate and professor of economics whose legacy is honored through the international Rafto Prize for human rights.
  • E. Harald Grenske
    Harald Grenske was a 10th-century Norwegian petty king of Vestfold and father of Saint Olaf II, who later became king and patron saint of Norway.
  • 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: Gunnar Fant
Triple: [Roman Jakobson, coAuthor, Gunnar Fant]
Generated description
Gunnar Fant was a pioneering Swedish speech scientist and phonetician renowned for his foundational work on the acoustic theory of speech production.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Gunnar Fant
Target entity description: Gunnar Fant was a pioneering Swedish speech scientist and phonetician renowned for his foundational work on the acoustic theory of speech production.
  • A. Gunnar Cauthery
    Gunnar Cauthery is an actor best known for his role in the television series "Mars."
  • B. Gunnar
    Gunnar is a masculine given name of Old Norse origin, commonly used in Scandinavian countries and associated with warriors or bold fighters.
  • C. Ulf Danielsson
    Ulf Danielsson is a Swedish theoretical physicist and cosmologist known for his work on string theory and the fundamental nature of the universe.
  • D. Thorolf Rafto
    Thorolf Rafto was a Norwegian human rights advocate and professor of economics whose legacy is honored through the international Rafto Prize for human rights.
  • E. Harald Grenske
    Harald Grenske was a 10th-century Norwegian petty king of Vestfold and father of Saint Olaf II, who later became king and patron saint of Norway.
  • 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_69c008fa64888190adae56c8f9ea4031 completed March 22, 2026, 3:21 p.m.
NER Named-entity recognition batch_69c01fb487648190948493fe96cec0ff completed March 22, 2026, 4:58 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0281bfcc48190a0e4e51b4dca5a4b completed March 22, 2026, 5:34 p.m.
NEDg Description generation batch_69c0362dc2648190b1cb81d6aa3050da completed March 22, 2026, 6:34 p.m.
NED2 Entity disambiguation (via description) batch_69c036adf9ac8190aed5688d67e52304 completed March 22, 2026, 6:36 p.m.
Created at: March 22, 2026, 3:35 p.m.