Triple

T2037092
Position Surface form Disambiguated ID Type / Status
Subject Lene Vestergaard Hau E44655 entity
Predicate familyName P18 FINISHED
Object Hau
Hau is the surname of Danish physicist Lene Vestergaard Hau, known for her pioneering work in slowing and stopping light.
 E228032 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: Hau | Statement: [Lene Vestergaard Hau, familyName, Hau]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Hau
Context triple: [Lene Vestergaard Hau, familyName, Hau]
  • A. Aua
    Aua is a coastal village on the island of Tutuila in American Samoa, known for its traditional Samoan community and proximity to Pago Pago Harbor.
  • B. Hekari
    Hekari is a regional dialect of the Kurmanji variety of the Kurdish language, spoken in parts of the Hakkari region.
  • C. Ehoiai
    Ehoiai is an alternative title for the ancient Greek Hesiodic Catalogue of Women, a fragmentary epic poem that recounts the genealogies and heroic myths of legendary women.
  • D. Hase
    The Hase is a river in northwestern Germany that flows through Lower Saxony and North Rhine-Westphalia, passing towns such as Quakenbrück before joining the Ems.
  • E. Harauti
    Harauti is an Indo-Aryan dialect of the Rajasthani language spoken primarily in the Hadoti region of Rajasthan, India.
  • 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: Hau
Triple: [Lene Vestergaard Hau, familyName, Hau]
Generated description
Hau is the surname of Danish physicist Lene Vestergaard Hau, known for her pioneering work in slowing and stopping light.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Hau
Target entity description: Hau is the surname of Danish physicist Lene Vestergaard Hau, known for her pioneering work in slowing and stopping light.
  • A. Aua
    Aua is a coastal village on the island of Tutuila in American Samoa, known for its traditional Samoan community and proximity to Pago Pago Harbor.
  • B. Hekari
    Hekari is a regional dialect of the Kurmanji variety of the Kurdish language, spoken in parts of the Hakkari region.
  • C. Ehoiai
    Ehoiai is an alternative title for the ancient Greek Hesiodic Catalogue of Women, a fragmentary epic poem that recounts the genealogies and heroic myths of legendary women.
  • D. Hase
    The Hase is a river in northwestern Germany that flows through Lower Saxony and North Rhine-Westphalia, passing towns such as Quakenbrück before joining the Ems.
  • E. Harauti
    Harauti is an Indo-Aryan dialect of the Rajasthani language spoken primarily in the Hadoti region of Rajasthan, India.
  • 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_69a889159ec481908f9e4472d9f480c7 completed March 4, 2026, 7:33 p.m.
NER Named-entity recognition batch_69abb9363b608190b42aa6d3f3fd78c4 completed March 7, 2026, 5:35 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae1ff38fb881909558e4d715a4d314 completed March 9, 2026, 1:18 a.m.
NEDg Description generation batch_69ae20946a288190a3bd2a19e3608e86 completed March 9, 2026, 1:21 a.m.
NED2 Entity disambiguation (via description) batch_69ae2109d17c819094a298a822064052 completed March 9, 2026, 1:23 a.m.
Created at: March 4, 2026, 7:39 p.m.