Triple

T13470456
Position Surface form Disambiguated ID Type / Status
Subject Vieux-Port – Hôtel de Ville E311615 entity
Predicate operator P179 FINISHED
Object RTM
RTM is the public transport authority that operates buses, trams, and metro services in Marseille and its surrounding metropolitan area in France.
 E1042245 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: RTM | Statement: [Vieux-Port – Hôtel de Ville, operator, RTM]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: RTM
Context triple: [Vieux-Port – Hôtel de Ville, operator, RTM]
  • A. RTM
    RTM is the commonly used abbreviation for Rosetta Terminology Mapping, a system for standardizing and aligning terminology across different datasets or domains.
  • B. RTM
    RTM is the IATA airport code for Rotterdam The Hague Airport, a regional international airport serving the Rotterdam–The Hague metropolitan area in the Netherlands.
  • C. RTMG
    RTMG is a specialized working group focused on analyzing emerging risks, trends, and methodological issues in its domain.
  • D. RMT
    RMT is the commonly used abbreviation for the United Nations Conference on Trade and Development’s annual Review of Maritime Transport report, which analyzes global maritime trade and shipping trends.
  • E. RTR
    RTR is a Swiss public broadcasting division that produces and distributes radio, television, and online content in the Romansh language.
  • 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: RTM
Triple: [Vieux-Port – Hôtel de Ville, operator, RTM]
Generated description
RTM is the public transport authority that operates buses, trams, and metro services in Marseille and its surrounding metropolitan area in France.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: RTM
Target entity description: RTM is the public transport authority that operates buses, trams, and metro services in Marseille and its surrounding metropolitan area in France.
  • A. RTM
    RTM is the commonly used abbreviation for Rosetta Terminology Mapping, a system for standardizing and aligning terminology across different datasets or domains.
  • B. RTM
    RTM is the IATA airport code for Rotterdam The Hague Airport, a regional international airport serving the Rotterdam–The Hague metropolitan area in the Netherlands.
  • C. RTMG
    RTMG is a specialized working group focused on analyzing emerging risks, trends, and methodological issues in its domain.
  • D. RMT
    RMT is the commonly used abbreviation for the United Nations Conference on Trade and Development’s annual Review of Maritime Transport report, which analyzes global maritime trade and shipping trends.
  • E. RTR
    RTR is a Swiss public broadcasting division that produces and distributes radio, television, and online content in the Romansh language.
  • 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_69d806a938b8819097ec43a2229fc7f9 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69dbaf22e5f88190b1078f006c8ef7c0 completed April 12, 2026, 2:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69f7462bcb848190804a48f1a50a0c71 completed May 3, 2026, 12:57 p.m.
NEDg Description generation batch_69f74af641f881908af981d251e671be completed May 3, 2026, 1:17 p.m.
NED2 Entity disambiguation (via description) batch_69f74b78bd508190a10708572a6e9309 completed May 3, 2026, 1:19 p.m.
Created at: April 9, 2026, 9:42 p.m.