Triple

T1422696
Position Surface form Disambiguated ID Type / Status
Subject François Certain Canrobert E30259 entity
Predicate familyName P18 FINISHED
Object Canrobert
Canrobert is a French surname most notably borne by Marshal François Certain Canrobert, a prominent 19th-century French military leader.
E163089 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: Canrobert | Statement: [François Certain Canrobert, familyName, Canrobert]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Canrobert
Context triple: [François Certain Canrobert, familyName, Canrobert]
  • A. Ramillies
    Ramillies is a village in present-day Belgium best known as the site of the 1706 Battle of Ramillies during the War of the Spanish Succession.
  • B. Choully
    Choully is a small wine-producing village in the commune of Satigny in the canton of Geneva, Switzerland.
  • C. Boncourt
    Boncourt is a locality known for its historic Château de Boncourt, reflecting its cultural and architectural heritage.
  • D. Haubourdin
    Haubourdin is a commune in northern France, located near Lille in the Nord department of the Hauts-de-France region.
  • E. Fourchambault, France
    Fourchambault, France is a small industrial town in the Nièvre department of central France, historically known for its steelworks and metallurgical industry.
  • 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: Canrobert
Triple: [François Certain Canrobert, familyName, Canrobert]
Generated description
Canrobert is a French surname most notably borne by Marshal François Certain Canrobert, a prominent 19th-century French military leader.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Canrobert
Target entity description: Canrobert is a French surname most notably borne by Marshal François Certain Canrobert, a prominent 19th-century French military leader.
  • A. Ramillies
    Ramillies is a village in present-day Belgium best known as the site of the 1706 Battle of Ramillies during the War of the Spanish Succession.
  • B. Choully
    Choully is a small wine-producing village in the commune of Satigny in the canton of Geneva, Switzerland.
  • C. Boncourt
    Boncourt is a locality known for its historic Château de Boncourt, reflecting its cultural and architectural heritage.
  • D. Haubourdin
    Haubourdin is a commune in northern France, located near Lille in the Nord department of the Hauts-de-France region.
  • E. Fourchambault, France
    Fourchambault, France is a small industrial town in the Nièvre department of central France, historically known for its steelworks and metallurgical industry.
  • 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_69a498fb823c8190a67ce4c4837e641a completed March 1, 2026, 7:52 p.m.
NER Named-entity recognition batch_69a4c4ba798881909c2259987248b030 completed March 1, 2026, 10:59 p.m.
NED1 Entity disambiguation (via context triple) batch_69ad0161e23c819099a1c72627f13dd0 completed March 8, 2026, 4:56 a.m.
NEDg Description generation batch_69ad01c53e808190824b9702c309f0a2 completed March 8, 2026, 4:57 a.m.
NED2 Entity disambiguation (via description) batch_69ad0241546881908f1044616255f146 completed March 8, 2026, 4:59 a.m.
Created at: March 1, 2026, 8 p.m.