Triple

T35869416
Position Surface form Disambiguated ID Type / Status
Subject Good Souls Better Angels E1037177 entity
Predicate hasTrack P3284 FINISHED
Object When the Way Gets Dark
"When the Way Gets Dark" is a song by American singer-songwriter Lucinda Williams from her critically acclaimed 2020 album *Good Souls Better Angels*.
E2161946 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: When the Way Gets Dark | Statement: [Good Souls Better Angels, hasTrack, When the Way Gets Dark]
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: When the Way Gets Dark
Triple: [Good Souls Better Angels, hasTrack, When the Way Gets Dark]
Generated description
"When the Way Gets Dark" is a song by American singer-songwriter Lucinda Williams from her critically acclaimed 2020 album *Good Souls Better Angels*.

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_69f76e1d279c8190843e5b64a0a12c3f completed May 3, 2026, 3:47 p.m.
NER Named-entity recognition batch_69f7a9c881ac8190baeebe3d7f69d0f6 completed May 3, 2026, 8:02 p.m.
NED1 Entity disambiguation (via context triple) batch_6a38ae1d6ab081909b312b1e961714f8 completed June 22, 2026, 3:38 a.m.
NEDg Description generation batch_6a38b056e91c81908896809d286b4b42 completed June 22, 2026, 3:47 a.m.
NED2 Entity disambiguation (via description) batch_6a38b0a4372c8190bb7cccc31a4a571e completed June 22, 2026, 3:48 a.m.
Created at: May 3, 2026, 4:06 p.m.