Triple

T23506422
Position Surface form Disambiguated ID Type / Status
Subject George van Driem E572292 entity
Predicate familyName P18 FINISHED
Object van Driem
Van Driem is a Dutch surname most prominently associated with linguist George van Driem, known for his work on Himalayan and Tibeto-Burman languages.
 E1589153 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: van Driem | Statement: [George van Driem, familyName, van Driem]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: van Driem
Context triple: [George van Driem, familyName, van Driem]
  • A. van Deurs
    van Deurs is a Danish surname most notably borne by Birgitte Eva van Deurs, a figure associated with Denmark.
  • B. van Heemstra
    Van Heemstra is a Dutch noble family name historically associated with aristocratic lineage in the Netherlands.
  • C. Van der Madeweg
    Van der Madeweg is a metro station in Amsterdam that serves as a stop on the city's rapid transit network.
  • D. van Rij
    van Rij is a Dutch surname most notably borne by politician and tax advisor Marnix van Rij.
  • E. van Wijnbergen
    Van Wijnbergen is a Dutch surname associated with individuals such as Everdine Huberta van Wijnbergen.
  • 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: van Driem
Triple: [George van Driem, familyName, van Driem]
Generated description
Van Driem is a Dutch surname most prominently associated with linguist George van Driem, known for his work on Himalayan and Tibeto-Burman languages.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: van Driem
Target entity description: Van Driem is a Dutch surname most prominently associated with linguist George van Driem, known for his work on Himalayan and Tibeto-Burman languages.
  • A. van Deurs
    van Deurs is a Danish surname most notably borne by Birgitte Eva van Deurs, a figure associated with Denmark.
  • B. van Heemstra
    Van Heemstra is a Dutch noble family name historically associated with aristocratic lineage in the Netherlands.
  • C. Van der Madeweg
    Van der Madeweg is a metro station in Amsterdam that serves as a stop on the city's rapid transit network.
  • D. van Rij
    van Rij is a Dutch surname most notably borne by politician and tax advisor Marnix van Rij.
  • E. van Wijnbergen
    Van Wijnbergen is a Dutch surname associated with individuals such as Everdine Huberta van Wijnbergen.
  • 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_69e245b5e4208190bac8a6509867e394 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1a9009ca081908c4cffb8c32293ec completed April 29, 2026, 6:45 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0c8277b97481909b1405fd7469b910 completed May 19, 2026, 3:32 p.m.
NEDg Description generation batch_6a0ca6f2d4288190b0b5fd46d2a387bf completed May 19, 2026, 6:07 p.m.
NED2 Entity disambiguation (via description) batch_6a0ca7f09af48190b7bfdae25d2f286b completed May 19, 2026, 6:12 p.m.
Created at: April 17, 2026, 6:07 p.m.