Triple

T1743413
Position Surface form Disambiguated ID Type / Status
Subject Giverny cemetery E38281 entity
Predicate hasAccessRoad P9041 FINISHED
Object D5 road
The D5 road is a regional roadway in France that provides access to local destinations such as the Giverny cemetery and surrounding areas.
 E211407 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: D5 road | Statement: [Giverny cemetery, hasAccessRoad, D5 road]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: D5 road
Context triple: [Giverny cemetery, hasAccessRoad, D5 road]
  • A. D559 road
    The D559 road is a coastal route in southeastern France that connects several towns along the French Riviera, including Cavalaire-sur-Mer.
  • B. A955 road
    The A955 road is a coastal route in Fife, Scotland, linking several towns along the north shore of the Firth of Forth, including Methil.
  • C. D970 road
    The D970 road is a departmental route in southern France that serves as a regional connector in and around the town of Tarascon.
  • D. A25 road
    The A25 road is an important east–west route in South East England that runs through Surrey and connects several towns between Guildford and Sevenoaks.
  • E. A52 road
    The A52 road is a major east–west route in England that runs across the East Midlands, linking cities such as Nottingham and Derby with coastal towns like Skegness.
  • 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: D5 road
Triple: [Giverny cemetery, hasAccessRoad, D5 road]
Generated description
The D5 road is a regional roadway in France that provides access to local destinations such as the Giverny cemetery and surrounding areas.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: D5 road
Target entity description: The D5 road is a regional roadway in France that provides access to local destinations such as the Giverny cemetery and surrounding areas.
  • A. D559 road
    The D559 road is a coastal route in southeastern France that connects several towns along the French Riviera, including Cavalaire-sur-Mer.
  • B. A955 road
    The A955 road is a coastal route in Fife, Scotland, linking several towns along the north shore of the Firth of Forth, including Methil.
  • C. D970 road
    The D970 road is a departmental route in southern France that serves as a regional connector in and around the town of Tarascon.
  • D. A25 road
    The A25 road is an important east–west route in South East England that runs through Surrey and connects several towns between Guildford and Sevenoaks.
  • E. A52 road
    The A52 road is a major east–west route in England that runs across the East Midlands, linking cities such as Nottingham and Derby with coastal towns like Skegness.
  • 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_69a8862b01a48190ab47209063af82d9 completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69aa63c836d48190bd44ea24977aba2d completed March 6, 2026, 5:19 a.m.
NED1 Entity disambiguation (via context triple) batch_69adeaca5f348190a8c1be9948d960e6 completed March 8, 2026, 9:31 p.m.
NEDg Description generation batch_69adeb6e8fe08190a4732d42aa15ee8e completed March 8, 2026, 9:34 p.m.
NED2 Entity disambiguation (via description) batch_69adebea03a08190bd055e3e6460b5f4 completed March 8, 2026, 9:36 p.m.
Created at: March 4, 2026, 7:31 p.m.