Triple

T11505377
Position Surface form Disambiguated ID Type / Status
Subject Princeton University Observatory E272768 entity
Predicate hasNotableMember P304 FINISHED
Object Jo Dunkley
Jo Dunkley is a British astrophysicist and cosmologist known for her work on the cosmic microwave background and the large-scale structure of the universe.
 E929794 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: Jo Dunkley | Statement: [Princeton University Observatory, hasNotableMember, Jo Dunkley]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Jo Dunkley
Context triple: [Princeton University Observatory, hasNotableMember, Jo Dunkley]
  • A. Sam McCandlish
    Sam McCandlish is a machine learning researcher known for his work on large-scale language models and contributions to influential AI research at OpenAI.
  • B. Lang Fisher
    Lang Fisher is a television writer, producer, and co-creator of the Netflix teen comedy series "Never Have I Ever."
  • C. Nick Daley
    Nick Daley is a fictional character from the "Night at the Museum" film series, known as the son of protagonist Larry Daley.
  • D. Adam Gough
    Adam Gough is a British film editor known for his work on acclaimed films such as "Da 5 Bloods" and "Roma."
  • E. Dan Janvey
    Dan Janvey is an American film producer known for his work on acclaimed independent films, including the Academy Award–winning "Nomadland."
  • 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: Jo Dunkley
Triple: [Princeton University Observatory, hasNotableMember, Jo Dunkley]
Generated description
Jo Dunkley is a British astrophysicist and cosmologist known for her work on the cosmic microwave background and the large-scale structure of the universe.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Jo Dunkley
Target entity description: Jo Dunkley is a British astrophysicist and cosmologist known for her work on the cosmic microwave background and the large-scale structure of the universe.
  • A. Sam McCandlish
    Sam McCandlish is a machine learning researcher known for his work on large-scale language models and contributions to influential AI research at OpenAI.
  • B. Lang Fisher
    Lang Fisher is a television writer, producer, and co-creator of the Netflix teen comedy series "Never Have I Ever."
  • C. Nick Daley
    Nick Daley is a fictional character from the "Night at the Museum" film series, known as the son of protagonist Larry Daley.
  • D. Adam Gough
    Adam Gough is a British film editor known for his work on acclaimed films such as "Da 5 Bloods" and "Roma."
  • E. Dan Janvey
    Dan Janvey is an American film producer known for his work on acclaimed independent films, including the Academy Award–winning "Nomadland."
  • 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_69d6aae2c3748190bed2ea50dfb160dc completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d86db2f4b08190801de1b773932f59 completed April 10, 2026, 3:25 a.m.
NED1 Entity disambiguation (via context triple) batch_69e624e6e5b88190a2c64dcea1d7791b completed April 20, 2026, 1:06 p.m.
NEDg Description generation batch_69e62cf224f881908badcdab6aea1aef completed April 20, 2026, 1:41 p.m.
NED2 Entity disambiguation (via description) batch_69e663ffedfc8190a2b51995c62d1e6b completed April 20, 2026, 5:36 p.m.
Created at: April 8, 2026, 9:36 p.m.