Triple

T14561458
Position Surface form Disambiguated ID Type / Status
Subject Line C (Strasbourg tram) E341674 entity
Predicate hasRouteDesignation P5539 FINISHED
Object C
C is a tram route designation used in the Strasbourg tramway network in France.
E1106663 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: C | Statement: [Line C (Strasbourg tram), hasRouteDesignation, C]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: C
Context triple: [Line C (Strasbourg tram), hasRouteDesignation, C]
  • A. C
    C is a foundational, general-purpose programming language known for its efficiency, low-level memory access, and influence on many later languages such as C++, Java, and Python.
  • B. C
    C is a local service on the New York City Subway that runs along the Eighth Avenue Line in Manhattan and continues through Brooklyn.
  • C. C
    C is the New York Stock Exchange ticker symbol for Citigroup Inc., a major global financial services and banking corporation.
  • D. C
    C is one of the three central women in Edward Albee’s play "Three Tall Women," representing a younger stage of the protagonist’s life and perspective.
  • E. C
    C is a Copenhagen S-train commuter rail line that runs through central Copenhagen and connects key suburban areas in the metropolitan network.
  • 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: C
Triple: [Line C (Strasbourg tram), hasRouteDesignation, C]
Generated description
C is a tram route designation used in the Strasbourg tramway network in France.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: C
Target entity description: C is a tram route designation used in the Strasbourg tramway network in France.
  • A. C
    C is a Copenhagen S-train commuter rail line that runs through central Copenhagen and connects key suburban areas in the metropolitan network.
  • B. C
    C is a light rail service designation used by the Los Angeles Metro system for one of its primary rail lines.
  • C. C
    C is a local service on the New York City Subway that runs along the Eighth Avenue Line in Manhattan and continues through Brooklyn.
  • D. C
    C is the New York Stock Exchange ticker symbol for Citigroup Inc., a major global financial services and banking corporation.
  • E. C
    C is the standard scholarly siglum for Codex Ephraemi Rescriptus, a 5th-century Greek biblical manuscript and palimpsest containing portions of the Old and New Testaments.
  • 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_69d822dcc6248190bed689984bceb0e2 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb389d0f48190a1d9d69456d1cbe1 completed April 14, 2026, 9:37 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd8ac294748190a4bfeed8c5fd9e94 completed May 8, 2026, 7:03 a.m.
NEDg Description generation batch_69fd8c3678048190a23b509e963c1ade completed May 8, 2026, 7:09 a.m.
NED2 Entity disambiguation (via description) batch_69fd8d609684819090a9c3f2304f4a6a completed May 8, 2026, 7:14 a.m.
Created at: April 10, 2026, 1:23 a.m.