Triple

T10257660
Position Surface form Disambiguated ID Type / Status
Subject Spaarne E240514 entity
Predicate hasBridge P386 FINISHED
Object Wittebrug
Wittebrug is a bridge spanning the Spaarne River in the Dutch city of Haarlem.
 E854544 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: Wittebrug | Statement: [Spaarne, hasBridge, Wittebrug]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Wittebrug
Context triple: [Spaarne, hasBridge, Wittebrug]
  • A. Willemsbrug
    Willemsbrug is a prominent red steel cable-stayed bridge in Rotterdam, Netherlands, spanning the Nieuwe Maas and connecting the city’s northern and southern banks.
  • B. Geeuwenbrug
    Geeuwenbrug is a small village in the Dutch province of Drenthe, situated within the municipality of Westerveld.
  • C. Prinses Irenebrug
    Prinses Irenebrug is a bridge in the Netherlands named after Princess Irene, serving as an important crossing over the Amsterdam–Rhine Canal.
  • D. Veerse Gatdam
    Veerse Gatdam is a Dutch dam and causeway that forms part of the Delta Works coastal defense system, separating the Veerse Meer lagoon from the North Sea.
  • E. Schoterbrug
    Schoterbrug is a bridge spanning the Spaarne River in Haarlem, Netherlands, serving as an important local traffic connection.
  • 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: Wittebrug
Triple: [Spaarne, hasBridge, Wittebrug]
Generated description
Wittebrug is a bridge spanning the Spaarne River in the Dutch city of Haarlem.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Wittebrug
Target entity description: Wittebrug is a bridge spanning the Spaarne River in the Dutch city of Haarlem.
  • A. Willemsbrug
    Willemsbrug is a prominent red steel cable-stayed bridge in Rotterdam, Netherlands, spanning the Nieuwe Maas and connecting the city’s northern and southern banks.
  • B. Geeuwenbrug
    Geeuwenbrug is a small village in the Dutch province of Drenthe, situated within the municipality of Westerveld.
  • C. Prinses Irenebrug
    Prinses Irenebrug is a bridge in the Netherlands named after Princess Irene, serving as an important crossing over the Amsterdam–Rhine Canal.
  • D. Veerse Gatdam
    Veerse Gatdam is a Dutch dam and causeway that forms part of the Delta Works coastal defense system, separating the Veerse Meer lagoon from the North Sea.
  • E. Schoterbrug
    Schoterbrug is a bridge spanning the Spaarne River in Haarlem, Netherlands, serving as an important local traffic connection.
  • 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_69d381a7e198819090280d5ab885d59e completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4d24de4588190b68fb3daa36dbd7d completed April 7, 2026, 9:45 a.m.
NED1 Entity disambiguation (via context triple) batch_69d71cdcdf8c81909f5a2be1c3aa03a0 completed April 9, 2026, 3:28 a.m.
NEDg Description generation batch_69d71f76e3cc8190b21a5fe8825caa2b completed April 9, 2026, 3:39 a.m.
NED2 Entity disambiguation (via description) batch_69d7319938ec8190a4a1a5f09832e3e3 completed April 9, 2026, 4:56 a.m.
Created at: April 6, 2026, 11:31 a.m.