Triple

T23588832
Position Surface form Disambiguated ID Type / Status
Subject Charles Martin Hall E582417 entity
Predicate notableStudentOf P4838 FINISHED
Object Frank Fanning Jewett
Frank Fanning Jewett was an American chemist and professor whose encouragement and instruction helped inspire Charles Martin Hall’s development of an economical process for producing aluminum.
 E1606461 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 Fanning Jewett | Statement: [Charles Martin Hall, notableStudentOf, Frank Fanning Jewett]
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 Fanning Jewett
Triple: [Charles Martin Hall, notableStudentOf, Frank Fanning Jewett]
Generated description
Frank Fanning Jewett was an American chemist and professor whose encouragement and instruction helped inspire Charles Martin Hall’s development of an economical process for producing aluminum.

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_69e248f9e0a08190814772847003b1ff completed April 17, 2026, 2:51 p.m.
NER Named-entity recognition batch_69f1b0336aec8190856aee4a8273c3e5 completed April 29, 2026, 7:16 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0f694f38208190b52fd5563abb3e31 completed May 21, 2026, 8:21 p.m.
NEDg Description generation batch_6a0f6d3d0b548190aa6de291bffd32ce completed May 21, 2026, 8:38 p.m.
NED2 Entity disambiguation (via description) batch_6a0f6db3e3c081909f81db7080f51351 completed May 21, 2026, 8:40 p.m.
Created at: April 17, 2026, 6:41 p.m.