Triple

T22889957
Position Surface form Disambiguated ID Type / Status
Subject Frank Butler E567709 entity
Predicate basedOn P98 FINISHED
Object Frank E. Butler
Frank E. Butler was a renowned 19th-century American sharpshooter best known as the husband and professional shooting partner of Annie Oakley in Buffalo Bill’s Wild West show.
 E2291411 NE FINISHED

How this triple was built (2 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: Frank E. Butler | Statement: [Frank Butler, basedOn, Frank E. Butler]
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: Frank E. Butler
Triple: [Frank Butler, basedOn, Frank E. Butler]
Generated description
Frank E. Butler was a renowned 19th-century American sharpshooter best known as the husband and professional shooting partner of Annie Oakley in Buffalo Bill’s Wild West show.

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_69e2458a92ec81908fc1cd5f6407d2ab completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17fc479d48190a8218eceaebd6cc8 completed April 29, 2026, 3:49 a.m.
NED1 Entity disambiguation (via context triple) batch_6a5c5a16c3d081909e7e037099c1852d completed July 19, 2026, 5:01 a.m.
NEDg Description generation batch_6a5c5bc7e94081909a01c163478fe41c completed July 19, 2026, 5:08 a.m.
NED2 Entity disambiguation (via description) batch_6a5c5c20b2e48190a11b58114e05aa07 completed July 19, 2026, 5:09 a.m.
Created at: April 17, 2026, 3:40 p.m.