Triple

T9218481
Position Surface form Disambiguated ID Type / Status
Subject Bertogne E221298 entity
Predicate hasRoadConnection P385 FINISHED
Object N826 road
The N826 road is a regional route in Belgium that connects the village of Bertogne with other nearby localities in the Walloon region.
E786055 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: N826 road | Statement: [Bertogne, hasRoadConnection, N826 road]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: N826 road
Context triple: [Bertogne, hasRoadConnection, N826 road]
  • A. N836 road
    The N836 road is a regional roadway in the Netherlands that connects the town of Tiel with other nearby localities in the Gelderland province.
  • B. N83 road
    The N83 road is a major national highway in eastern France that connects several towns and cities in the Jura and surrounding regions.
  • C. N286 road
    The N286 road is a regional roadway in the Netherlands that connects the town of Tholen with other nearby municipalities in the province of Zeeland.
  • D. N8 road
    The N8 road is a regional route in Belgium that connects the coastal city of Veurne with inland towns and cities, serving as an important link between West Flanders and the interior.
  • E. N287 road
    The N287 road is a regional roadway in Belgium that connects local towns and intersects with major routes such as the N57.
  • 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: N826 road
Triple: [Bertogne, hasRoadConnection, N826 road]
Generated description
The N826 road is a regional route in Belgium that connects the village of Bertogne with other nearby localities in the Walloon region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: N826 road
Target entity description: The N826 road is a regional route in Belgium that connects the village of Bertogne with other nearby localities in the Walloon region.
  • A. N836 road
    The N836 road is a regional roadway in the Netherlands that connects the town of Tiel with other nearby localities in the Gelderland province.
  • B. N83 road
    The N83 road is a major national highway in eastern France that connects several towns and cities in the Jura and surrounding regions.
  • C. N286 road
    The N286 road is a regional roadway in the Netherlands that connects the town of Tholen with other nearby municipalities in the province of Zeeland.
  • D. N8 road
    The N8 road is a regional route in Belgium that connects the coastal city of Veurne with inland towns and cities, serving as an important link between West Flanders and the interior.
  • E. N287 road
    The N287 road is a regional roadway in Belgium that connects local towns and intersects with major routes such as the N57.
  • 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_69ca83eae42c8190a0ea9e040710a277 completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69ccda730f688190b64b2cc8c4898ac3 completed April 1, 2026, 8:42 a.m.
NED1 Entity disambiguation (via context triple) batch_69d0662427dc81908cb9bfacc5b9e0f5 completed April 4, 2026, 1:15 a.m.
NEDg Description generation batch_69d0697b506c8190b14acbec1266f4bc completed April 4, 2026, 1:29 a.m.
NED2 Entity disambiguation (via description) batch_69d06a01520081908f697cf285c88c00 completed April 4, 2026, 1:31 a.m.
Created at: March 30, 2026, 7:27 p.m.