Triple

T5415116
Position Surface form Disambiguated ID Type / Status
Subject Lyon Arboretum E121110 entity
Predicate namedAfter P63 FINISHED
Object Harold L. Lyon
Harold L. Lyon was a botanist and educator whose work in tropical plant research and conservation led to an arboretum in Hawaii being named in his honor.
 E520206 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: Harold L. Lyon | Statement: [Lyon Arboretum, namedAfter, Harold L. Lyon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Harold L. Lyon
Context triple: [Lyon Arboretum, namedAfter, Harold L. Lyon]
  • A. Harold Bruce Welch
    Harold Bruce Welch was an American businessman and the father of former First Lady Laura Bush.
  • B. Frank P. Keller
    Frank P. Keller is a film editor best known for his Academy Award-winning work on the 1968 action film "Bullitt."
  • C. Kenneth Hayes Miller
    Kenneth Hayes Miller was an influential American painter and teacher associated with the Ashcan School, known for his urban genre scenes and for mentoring many prominent 20th-century artists.
  • D. Philip J. Suess
    Philip J. Suess is an American politician who serves as the mayor of Wheaton, Illinois.
  • E. Fred M. Wilcox
    Fred M. Wilcox was an American film director best known for the science fiction classic "Forbidden Planet" and the family film "Lassie Come Home."
  • 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: Harold L. Lyon
Triple: [Lyon Arboretum, namedAfter, Harold L. Lyon]
Generated description
Harold L. Lyon was a botanist and educator whose work in tropical plant research and conservation led to an arboretum in Hawaii being named in his honor.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Harold L. Lyon
Target entity description: Harold L. Lyon was a botanist and educator whose work in tropical plant research and conservation led to an arboretum in Hawaii being named in his honor.
  • A. Harold Bruce Welch
    Harold Bruce Welch was an American businessman and the father of former First Lady Laura Bush.
  • B. Frank P. Keller
    Frank P. Keller is a film editor best known for his Academy Award-winning work on the 1968 action film "Bullitt."
  • C. Kenneth Hayes Miller
    Kenneth Hayes Miller was an influential American painter and teacher associated with the Ashcan School, known for his urban genre scenes and for mentoring many prominent 20th-century artists.
  • D. Philip J. Suess
    Philip J. Suess is an American politician who serves as the mayor of Wheaton, Illinois.
  • E. Fred M. Wilcox
    Fred M. Wilcox was an American film director best known for the science fiction classic "Forbidden Planet" and the family film "Lassie Come Home."
  • 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_69bd463a41cc8190b32ff5af2b96ca93 completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd87be754c81909c0d0df6216cae46 completed March 20, 2026, 5:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf4121edc4819081fdb79dcc182540 completed March 22, 2026, 1:08 a.m.
NEDg Description generation batch_69bf428d60348190a1368e81d8bf354d completed March 22, 2026, 1:14 a.m.
NED2 Entity disambiguation (via description) batch_69bf42e470e0819091d1410e717c2470 completed March 22, 2026, 1:16 a.m.
Created at: March 20, 2026, 2:05 p.m.