Triple

T15403736
Position Surface form Disambiguated ID Type / Status
Subject Lys River E368392 entity
Predicate hasTributary P415 FINISHED
Object Lawe
The Lawe is a river in northern France that flows through the Pas-de-Calais department and joins the Lys River.
 E1155296 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: Lawe | Statement: [Lys River, hasTributary, Lawe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Lawe
Context triple: [Lys River, hasTributary, Lawe]
  • A. Alannys Harlaw
    Alannys Harlaw is a noblewoman of House Harlaw in the Iron Islands and the wife of Balon Greyjoy in George R. R. Martin’s A Song of Ice and Fire series.
  • B. Gualter
    Gualter is a given name, particularly used in Portuguese and Spanish contexts, that is cognate with the French name Gauthier and ultimately related to the name Walter.
  • C. Lewelin
    Lewelin is a variant spelling of the Welsh given name Llewelyn, historically borne by several medieval Welsh princes and nobles.
  • D. Laylaw
    Laylaw is a hip-hop music producer best known for his work with West Coast rap artists in the 1990s.
  • E. Bigod
    Bigod is an Anglo-Norman noble family prominent in medieval England, particularly known for holding the earldom of Norfolk and playing key roles in royal politics.
  • 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: Lawe
Triple: [Lys River, hasTributary, Lawe]
Generated description
The Lawe is a river in northern France that flows through the Pas-de-Calais department and joins the Lys River.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Lawe
Target entity description: The Lawe is a river in northern France that flows through the Pas-de-Calais department and joins the Lys River.
  • A. Alannys Harlaw
    Alannys Harlaw is a noblewoman of House Harlaw in the Iron Islands and the wife of Balon Greyjoy in George R. R. Martin’s A Song of Ice and Fire series.
  • B. Gualter
    Gualter is a given name, particularly used in Portuguese and Spanish contexts, that is cognate with the French name Gauthier and ultimately related to the name Walter.
  • C. Lewelin
    Lewelin is a variant spelling of the Welsh given name Llewelyn, historically borne by several medieval Welsh princes and nobles.
  • D. Laylaw
    Laylaw is a hip-hop music producer best known for his work with West Coast rap artists in the 1990s.
  • E. Bigod
    Bigod is an Anglo-Norman noble family prominent in medieval England, particularly known for holding the earldom of Norfolk and playing key roles in royal politics.
  • 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_69d85a16c68c819099c1b547fbc87b32 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e03e8fde64819082ec0c68df305561 completed April 16, 2026, 1:42 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff13584f8881908b2527c51f85ae28 completed May 9, 2026, 10:58 a.m.
NEDg Description generation batch_69ff145ac8e081908b075cee67e82aa3 completed May 9, 2026, 11:02 a.m.
NED2 Entity disambiguation (via description) batch_69ff1509e5a48190b69f1a44d793e07d completed May 9, 2026, 11:05 a.m.
Created at: April 10, 2026, 3:19 a.m.