Triple

T2122325
Position Surface form Disambiguated ID Type / Status
Subject Seine-et-Marne E43951 entity
Predicate ISO3166-2 P189 FINISHED
Object FR-77
FR-77 is the ISO 3166-2 code designating the French department of Seine-et-Marne in the Île-de-France region.
 E235953 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: FR-77 | Statement: [Seine-et-Marne, ISO3166-2, FR-77]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: FR-77
Context triple: [Seine-et-Marne, ISO3166-2, FR-77]
  • A. FR3
    FR3 was a former French public television channel and network that later became part of France Télévisions.
  • B. MF 77
    MF 77 is a steel-wheeled electric multiple unit train used on several lines of the Paris Métro, introduced in the late 1970s to modernize the network’s rolling stock.
  • C. French D900
    The French D900 is a departmental road in southeastern France that serves as a key route through the Alps, connecting to the Col de Larche mountain pass near the Italian border.
  • D. MF 67
    MF 67 is a class of steel-wheeled electric multiple unit trains that have long served as a primary rolling stock type on the Paris Métro.
  • E. UP-78
    UP-78 is the vehicle registration code assigned to motor vehicles registered in Kanpur, Uttar Pradesh, India.
  • 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: FR-77
Triple: [Seine-et-Marne, ISO3166-2, FR-77]
Generated description
FR-77 is the ISO 3166-2 code designating the French department of Seine-et-Marne in the Île-de-France region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: FR-77
Target entity description: FR-77 is the ISO 3166-2 code designating the French department of Seine-et-Marne in the Île-de-France region.
  • A. FR3
    FR3 was a former French public television channel and network that later became part of France Télévisions.
  • B. MF 77
    MF 77 is a steel-wheeled electric multiple unit train used on several lines of the Paris Métro, introduced in the late 1970s to modernize the network’s rolling stock.
  • C. French D900
    The French D900 is a departmental road in southeastern France that serves as a key route through the Alps, connecting to the Col de Larche mountain pass near the Italian border.
  • D. MF 67
    MF 67 is a class of steel-wheeled electric multiple unit trains that have long served as a primary rolling stock type on the Paris Métro.
  • E. UP-78
    UP-78 is the vehicle registration code assigned to motor vehicles registered in Kanpur, Uttar Pradesh, India.
  • 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_69a88717cfe48190b7ecdd68c824848a completed March 4, 2026, 7:25 p.m.
NER Named-entity recognition batch_69abbb51e8088190a1aeafee4e8dff63 completed March 7, 2026, 5:44 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae51999ca08190a726040df6825ba5 completed March 9, 2026, 4:50 a.m.
NEDg Description generation batch_69ae5209ae40819095e02cafb8112a1f completed March 9, 2026, 4:52 a.m.
NED2 Entity disambiguation (via description) batch_69ae529375788190aead19ec0874f11e completed March 9, 2026, 4:54 a.m.
Created at: March 4, 2026, 7:44 p.m.