Triple

T14469454
Position Surface form Disambiguated ID Type / Status
Subject Yle Fem E358798 entity
Predicate formerName P65 FINISHED
Object FST
FST was the former name of Yle Fem, the Swedish-language television channel operated by Finland’s national public broadcaster Yle.
 E1101258 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: FST | Statement: [Yle Fem, formerName, FST]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: FST
Context triple: [Yle Fem, formerName, FST]
  • A. FST
    FST is the three-letter National Rail station code for London’s Fenchurch Street railway station, a central terminus serving commuter routes in the east of England.
  • B. FST
    FST is the commonly used abbreviation for the UK government ministerial post of Financial Secretary to the Treasury, a key role within HM Treasury responsible for economic and financial matters.
  • C. FOST
    FOST is the French Navy’s Strategic Oceanic Force responsible for operating France’s nuclear ballistic missile submarine deterrent.
  • D. FSE
    FSE (Fast Software Encryption) is a leading international research conference focused on the design and analysis of symmetric-key cryptographic primitives and algorithms.
  • E. FSE
    FSE is the Faculty of Science and Engineering at the University of Groningen, encompassing a broad range of natural sciences, engineering, and technology disciplines.
  • 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: FST
Triple: [Yle Fem, formerName, FST]
Generated description
FST was the former name of Yle Fem, the Swedish-language television channel operated by Finland’s national public broadcaster Yle.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: FST
Target entity description: FST was the former name of Yle Fem, the Swedish-language television channel operated by Finland’s national public broadcaster Yle.
  • A. FST
    FST is the commonly used abbreviation for the UK government ministerial post of Financial Secretary to the Treasury, a key role within HM Treasury responsible for economic and financial matters.
  • B. FST
    FST is the three-letter National Rail station code for London’s Fenchurch Street railway station, a central terminus serving commuter routes in the east of England.
  • C. FOST
    FOST is the French Navy’s Strategic Oceanic Force responsible for operating France’s nuclear ballistic missile submarine deterrent.
  • D. FSE
    FSE is the Faculty of Science and Engineering at the University of Groningen, encompassing a broad range of natural sciences, engineering, and technology disciplines.
  • E. FSE
    FSE (Fast Software Encryption) is a leading international research conference focused on the design and analysis of symmetric-key cryptographic primitives and algorithms.
  • 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_69d827966698819082e140837737501d completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de91f969788190a5114f92d7159aae completed April 14, 2026, 7:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd649beec88190861abb52c5a2733e completed May 8, 2026, 4:20 a.m.
NEDg Description generation batch_69fd67b1ed2081908d3de6514078be49 completed May 8, 2026, 4:33 a.m.
NED2 Entity disambiguation (via description) batch_69fd682f28948190adc037c18c7deb93 completed May 8, 2026, 4:35 a.m.
Created at: April 10, 2026, 1:20 a.m.