Triple

T10471548
Position Surface form Disambiguated ID Type / Status
Subject Service historique de la Défense E246934 entity
Predicate shortName P43 FINISHED
Object SHD
SHD is the French Defence Historical Service, the national institution responsible for preserving and providing access to France’s military archives and historical records.
 E865543 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: SHD | Statement: [Service historique de la Défense, shortName, SHD]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SHD
Context triple: [Service historique de la Défense, shortName, SHD]
  • A. SHF
    SHF is the National Rail station code for Sheffield railway station, a major rail hub in South Yorkshire, England.
  • B. SH
    SH is the common abbreviation for Södertörn University, a higher education institution located in the Stockholm region of Sweden.
  • C. SH
    SH is the vehicle registration code for the Swiss canton of Schaffhausen.
  • D. Sh1
    Sh1 is a Georgian mountain road route that traverses the Goderdzi Pass, connecting regions across the Lesser Caucasus.
  • E. SHH
    SHH is the railway station code used to identify Shanghai South Railway Station in China’s rail 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: SHD
Triple: [Service historique de la Défense, shortName, SHD]
Generated description
SHD is the French Defence Historical Service, the national institution responsible for preserving and providing access to France’s military archives and historical records.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SHD
Target entity description: SHD is the French Defence Historical Service, the national institution responsible for preserving and providing access to France’s military archives and historical records.
  • A. SHF
    SHF is the National Rail station code for Sheffield railway station, a major rail hub in South Yorkshire, England.
  • B. SH
    SH is the common abbreviation for Södertörn University, a higher education institution located in the Stockholm region of Sweden.
  • C. SH
    SH is the vehicle registration code for the Swiss canton of Schaffhausen.
  • D. Sh1
    Sh1 is a Georgian mountain road route that traverses the Goderdzi Pass, connecting regions across the Lesser Caucasus.
  • E. SHH
    SHH is the railway station code used to identify Shanghai South Railway Station in China’s rail network.
  • 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_69d381c16c248190a2fe5b471e584e9c completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d5094cec788190a485c5c9e7cd024a completed April 7, 2026, 1:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69d8a0094910819094d492c87b31898e completed April 10, 2026, 7 a.m.
NEDg Description generation batch_69d8a45e5a108190ba8e6ba4af858b19 completed April 10, 2026, 7:18 a.m.
NED2 Entity disambiguation (via description) batch_69d8a890c6b081908e57cc74f18d788b completed April 10, 2026, 7:36 a.m.
Created at: April 6, 2026, 12:20 p.m.