Triple

T1735992
Position Surface form Disambiguated ID Type / Status
Subject SNCF E37919 entity
Predicate subsidiary P258 FINISHED
Object Geodis
Geodis is a global logistics and supply chain management company providing freight forwarding, contract logistics, and transportation services.
E194410 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: Geodis | Statement: [SNCF, subsidiary, Geodis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Geodis
Context triple: [SNCF, subsidiary, Geodis]
  • A. DHL
    DHL is a global logistics and courier company known for its international express mail, freight transportation, and supply chain management services.
  • B. DHL
    DHL is the Dag Hammarskjöld Library, the United Nations’ main research and information resource center located at its headquarters in New York.
  • C. YRC Worldwide
    YRC Worldwide is a large American less-than-truckload (LTL) freight transportation and logistics company headquartered in Overland Park, Kansas.
  • D. FedEx
    FedEx is a global courier delivery services company known for its overnight shipping and pioneering real-time package tracking.
  • E. Tractebel
    Tractebel is an international engineering and consulting company specializing in energy, water, and infrastructure projects.
  • 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: Geodis
Triple: [SNCF, subsidiary, Geodis]
Generated description
Geodis is a global logistics and supply chain management company providing freight forwarding, contract logistics, and transportation services.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Geodis
Target entity description: Geodis is a global logistics and supply chain management company providing freight forwarding, contract logistics, and transportation services.
  • A. DHL
    DHL is a global logistics and courier company known for its international express mail, freight transportation, and supply chain management services.
  • B. DHL
    DHL is the Dag Hammarskjöld Library, the United Nations’ main research and information resource center located at its headquarters in New York.
  • C. YRC Worldwide
    YRC Worldwide is a large American less-than-truckload (LTL) freight transportation and logistics company headquartered in Overland Park, Kansas.
  • D. FedEx
    FedEx is a global courier delivery services company known for its overnight shipping and pioneering real-time package tracking.
  • E. Tractebel
    Tractebel is an international engineering and consulting company specializing in energy, water, and infrastructure projects.
  • 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_69a8861cc6ac8190ac0b2e31ccf62851 completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69aa63a369048190bae352573f5082f1 completed March 6, 2026, 5:18 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad8b008b7881909ac568af010bcf99 completed March 8, 2026, 2:43 p.m.
NEDg Description generation batch_69ad979dc1dc81908b64e57298ae6017 completed March 8, 2026, 3:37 p.m.
NED2 Entity disambiguation (via description) batch_69ad9836f4c8819098ba033b5f0d2a33 completed March 8, 2026, 3:39 p.m.
Created at: March 4, 2026, 7:30 p.m.