Triple

T23378107
Position Surface form Disambiguated ID Type / Status
Subject Bound by Law? Tales from the Public Domain E593661 entity
Predicate author P4 FINISHED
Object Jennifer Jenkins
Jennifer Jenkins is a legal scholar and educator known for her work on copyright, the public domain, and creative commons, including co-authoring the comic book "Bound by Law? Tales from the Public Domain."
E1637229 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: Jennifer Jenkins | Statement: [Bound by Law? Tales from the Public Domain, author, Jennifer Jenkins]
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: Jennifer Jenkins
Triple: [Bound by Law? Tales from the Public Domain, author, Jennifer Jenkins]
Generated description
Jennifer Jenkins is a legal scholar and educator known for her work on copyright, the public domain, and creative commons, including co-authoring the comic book "Bound by Law? Tales from the Public Domain."

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_69e25d268a50819095f2fd479da8ef3f completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f1a3b526ec8190b0304c72a9010abb completed April 29, 2026, 6:22 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0fee4023cc81908f5b8736cf69aa9d completed May 22, 2026, 5:48 a.m.
NEDg Description generation batch_6a0feecd5c2481909dc01db940d1a386 completed May 22, 2026, 5:51 a.m.
NED2 Entity disambiguation (via description) batch_6a0fef266b788190a03a7cd43444126d completed May 22, 2026, 5:52 a.m.
Created at: April 17, 2026, 5:33 p.m.