Triple

T4260674
Position Surface form Disambiguated ID Type / Status
Subject David Rumsey Map Center E96095 entity
Predicate namedAfter P63 FINISHED
Object David Rumsey
David Rumsey is an American map collector and historian renowned for his extensive collection of historical maps and cartographic materials.
 E425717 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: David Rumsey | Statement: [David Rumsey Map Center, namedAfter, David Rumsey]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: David Rumsey
Context triple: [David Rumsey Map Center, namedAfter, David Rumsey]
  • A. J. W. Arrowsmith
    J. W. Arrowsmith was a prominent 19th-century British publishing firm based in Bristol, known for issuing popular novels and literary works.
  • B. William Tharp
    William Tharp was a 19th-century American politician who served as the 36th Governor of Delaware.
  • C. Paul Fisher
    Paul Fisher is a film director and screenwriter best known for his work on animated features such as The Lego Ninjago Movie.
  • D. Thomas Rivers
    Thomas Rivers was a pioneering 19th-century English nurseryman and horticulturist renowned for developing and popularizing many new fruit tree varieties.
  • E. Robert Simonds
    Robert Simonds is an American film producer and studio executive known for producing a string of successful Hollywood comedies and founding the media company STX Entertainment.
  • 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: David Rumsey
Triple: [David Rumsey Map Center, namedAfter, David Rumsey]
Generated description
David Rumsey is an American map collector and historian renowned for his extensive collection of historical maps and cartographic materials.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: David Rumsey
Target entity description: David Rumsey is an American map collector and historian renowned for his extensive collection of historical maps and cartographic materials.
  • A. J. W. Arrowsmith
    J. W. Arrowsmith was a prominent 19th-century British publishing firm based in Bristol, known for issuing popular novels and literary works.
  • B. William Tharp
    William Tharp was a 19th-century American politician who served as the 36th Governor of Delaware.
  • C. Paul Fisher
    Paul Fisher is a film director and screenwriter best known for his work on animated features such as The Lego Ninjago Movie.
  • D. Thomas Rivers
    Thomas Rivers was a pioneering 19th-century English nurseryman and horticulturist renowned for developing and popularizing many new fruit tree varieties.
  • E. Robert Simonds
    Robert Simonds is an American film producer and studio executive known for producing a string of successful Hollywood comedies and founding the media company STX Entertainment.
  • 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_69b3454095ac81909c2494f7ff294af1 completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b34f8103b48190934a810faafa6cb7 completed March 12, 2026, 11:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5b78c93c48190a4274f0de3fc2d25 completed March 14, 2026, 7:31 p.m.
NEDg Description generation batch_69b5b85f31d481908f85ea08b9af5b52 completed March 14, 2026, 7:34 p.m.
NED2 Entity disambiguation (via description) batch_69b5b8d0fc1c8190908724ea4f7c3d17 completed March 14, 2026, 7:36 p.m.
Created at: March 12, 2026, 11:06 p.m.