Triple

T16332538
Position Surface form Disambiguated ID Type / Status
Subject Grenoble tramway E396589 entity
Predicate operator P179 FINISHED
Object SEMITAG
SEMITAG is the public transport company responsible for operating the tram and bus network in the Grenoble metropolitan area in France.
 E1207899 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: SEMITAG | Statement: [Grenoble tramway, operator, SEMITAG]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SEMITAG
Context triple: [Grenoble tramway, operator, SEMITAG]
  • A. Tegsedi
    Tegsedi is an antisense oligonucleotide drug used to treat hereditary transthyretin-mediated amyloidosis by reducing the production of the transthyretin protein.
  • B. SEMAL
    SEMAL is the UN/LOCODE designation for the port and transport location associated with Lake Mälaren in Sweden.
  • C. SEMMARIS
    SEMMARIS is the semi-public company that manages and develops the Rungis International Market, one of the world’s largest wholesale food markets near Paris.
  • D. SÉG
    SÉG is the station code for Ségur, a Paris Métro station on Line 10 in the 15th arrondissement of Paris, France.
  • E. Sema
    Sema is a Russian diminutive form of the male given name Semyon.
  • 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: SEMITAG
Triple: [Grenoble tramway, operator, SEMITAG]
Generated description
SEMITAG is the public transport company responsible for operating the tram and bus network in the Grenoble metropolitan area in France.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SEMITAG
Target entity description: SEMITAG is the public transport company responsible for operating the tram and bus network in the Grenoble metropolitan area in France.
  • A. Tegsedi
    Tegsedi is an antisense oligonucleotide drug used to treat hereditary transthyretin-mediated amyloidosis by reducing the production of the transthyretin protein.
  • B. SEMAL
    SEMAL is the UN/LOCODE designation for the port and transport location associated with Lake Mälaren in Sweden.
  • C. SEMMARIS
    SEMMARIS is the semi-public company that manages and develops the Rungis International Market, one of the world’s largest wholesale food markets near Paris.
  • D. SÉG
    SÉG is the station code for Ségur, a Paris Métro station on Line 10 in the 15th arrondissement of Paris, France.
  • E. Sema
    Sema is a Russian diminutive form of the male given name Semyon.
  • 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_69d87f255b788190a400eba031dd85d8 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e2c4e0b1388190824b286e8452fb32 completed April 17, 2026, 11:40 p.m.
NED1 Entity disambiguation (via context triple) batch_6a002613c0e88190b91da8eba683c864 completed May 10, 2026, 6:30 a.m.
NEDg Description generation batch_6a0027854ce48190ad3fb09ecd7e2b9e completed May 10, 2026, 6:36 a.m.
NED2 Entity disambiguation (via description) batch_6a0029f138d88190bf240ca524d9ad0a completed May 10, 2026, 6:47 a.m.
Created at: April 10, 2026, 5:07 a.m.