Triple

T16101656
Position Surface form Disambiguated ID Type / Status
Subject Lee Bollinger E390634 entity
Predicate familyName P18 FINISHED
Object Bollinger
Bollinger is a surname most prominently associated with Lee Bollinger, the American legal scholar and longtime president of Columbia University.
E1193864 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: Bollinger | Statement: [Lee Bollinger, familyName, Bollinger]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bollinger
Context triple: [Lee Bollinger, familyName, Bollinger]
  • A. Bonger
    Bonger is a Dutch surname most notably associated with Johanna van Gogh-Bonger, the key figure in preserving and promoting Vincent van Gogh’s artistic legacy.
  • B. Boll
    Boll is a district or locality within the town of Oberndorf am Neckar in the German state of Baden-Württemberg.
  • C. Hulbert
    Hulbert is a small rural community located within the Township of South Dundas in eastern Ontario, Canada.
  • D. Tobin
    Tobin is the given name of Tobin Heath, an American professional soccer player and multiple-time FIFA Women's World Cup champion.
  • E. Briscoe
    Briscoe is a surname most notably associated with Dolph Briscoe, a prominent American rancher and politician who served as governor of Texas.
  • 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: Bollinger
Triple: [Lee Bollinger, familyName, Bollinger]
Generated description
Bollinger is a surname most prominently associated with Lee Bollinger, the American legal scholar and longtime president of Columbia University.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Bollinger
Target entity description: Bollinger is a surname most prominently associated with Lee Bollinger, the American legal scholar and longtime president of Columbia University.
  • A. Bonger
    Bonger is a Dutch surname most notably associated with Johanna van Gogh-Bonger, the key figure in preserving and promoting Vincent van Gogh’s artistic legacy.
  • B. Boll
    Boll is a district or locality within the town of Oberndorf am Neckar in the German state of Baden-Württemberg.
  • C. Hulbert
    Hulbert is a small rural community located within the Township of South Dundas in eastern Ontario, Canada.
  • D. Tobin
    Tobin is the given name of Tobin Heath, an American professional soccer player and multiple-time FIFA Women's World Cup champion.
  • E. Briscoe
    Briscoe is a surname most notably associated with Dolph Briscoe, a prominent American rancher and politician who served as governor of Texas.
  • 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_69d87f198bc48190a8b7e53ca15b7ead completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e1ff68686481909517eed4266729ca completed April 17, 2026, 9:37 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffeb9d6140819087f9b3dc549c4aec completed May 10, 2026, 2:21 a.m.
NEDg Description generation batch_69ffec273abc8190b050c50a395488ba completed May 10, 2026, 2:23 a.m.
NED2 Entity disambiguation (via description) batch_69ffecbd817881909cd8e8c69be1726f completed May 10, 2026, 2:26 a.m.
Created at: April 10, 2026, 5 a.m.