Triple

T1779367
Position Surface form Disambiguated ID Type / Status
Subject French Republic E39253 entity
Predicate internetTLD P248 FINISHED
Object .tf
.tf is the country code top-level domain (ccTLD) designated for the French Southern and Antarctic Lands, an overseas territory of France.
 E199808 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: .tf | Statement: [French Republic, internetTLD, .tf]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: .tf
Context triple: [French Republic, internetTLD, .tf]
  • A. TF
    TF is the French abbreviation for the Federal Supreme Court of Switzerland, the country’s highest judicial authority.
  • B. TF
    TF is the vehicle registration code used for motor vehicles registered in the Spanish province of Santa Cruz de Tenerife in the Canary Islands.
  • C. FT
    FT is the Faculty of Theology at the University of Geneva, a higher education institution specializing in theological and religious studies.
  • D. TFN
    TFN is the IATA airport code for Tenerife North Airport, a major airport serving the island of Tenerife in Spain’s Canary Islands.
  • E. FTTA
    FTTA is a U.S. law that promotes collaboration and technology transfer between federal laboratories and the private sector to commercialize government-funded innovations.
  • 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: .tf
Triple: [French Republic, internetTLD, .tf]
Generated description
.tf is the country code top-level domain (ccTLD) designated for the French Southern and Antarctic Lands, an overseas territory of France.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: .tf
Target entity description: .tf is the country code top-level domain (ccTLD) designated for the French Southern and Antarctic Lands, an overseas territory of France.
  • A. TF
    TF is the French abbreviation for the Federal Supreme Court of Switzerland, the country’s highest judicial authority.
  • B. TF
    TF is the vehicle registration code used for motor vehicles registered in the Spanish province of Santa Cruz de Tenerife in the Canary Islands.
  • C. FT
    FT is the Faculty of Theology at the University of Geneva, a higher education institution specializing in theological and religious studies.
  • D. TFN
    TFN is the IATA airport code for Tenerife North Airport, a major airport serving the island of Tenerife in Spain’s Canary Islands.
  • E. FTTA
    FTTA is a U.S. law that promotes collaboration and technology transfer between federal laboratories and the private sector to commercialize government-funded innovations.
  • 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_69a88630519c8190a17addd83c4a3ef4 completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69aa64e07bd081908e442c1004cdad61 completed March 6, 2026, 5:23 a.m.
NED1 Entity disambiguation (via context triple) batch_69ada99d12f88190a9daec1b7dd64e67 completed March 8, 2026, 4:53 p.m.
NEDg Description generation batch_69adab04b5688190afb3418e9b9da845 completed March 8, 2026, 4:59 p.m.
NED2 Entity disambiguation (via description) batch_69adaeaf81e881908f99f5d948e3557b completed March 8, 2026, 5:15 p.m.
Created at: March 4, 2026, 7:31 p.m.