Triple

T31164962
Position Surface form Disambiguated ID Type / Status
Subject Word of Mouth E794443 entity
Predicate hasTrack P3284 FINISHED
Object Living on a Thin Line
"Living on a Thin Line" is a song by the Kinks, written and sung by guitarist Dave Davies, noted for its darker tone and commentary on British society.
 E1949755 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: Living on a Thin Line | Statement: [Word of Mouth, hasTrack, Living on a Thin Line]
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: Living on a Thin Line
Triple: [Word of Mouth, hasTrack, Living on a Thin Line]
Generated description
"Living on a Thin Line" is a song by the Kinks, written and sung by guitarist Dave Davies, noted for its darker tone and commentary on British society.

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_69f224d504908190b01278dcb7fc3fa7 completed April 29, 2026, 3:33 p.m.
NER Named-entity recognition batch_69f69851345081908bcd0a000f68a8ef completed May 3, 2026, 12:35 a.m.
NED1 Entity disambiguation (via context triple) batch_6a29472ec64081909d65baea82264d67 completed June 10, 2026, 11:14 a.m.
NEDg Description generation batch_6a29482e8bc48190a1d257c7286b1ab1 completed June 10, 2026, 11:19 a.m.
NED2 Entity disambiguation (via description) batch_6a294eea0f148190a57b7ab05b9f0227 completed June 10, 2026, 11:47 a.m.
Created at: April 29, 2026, 9:07 p.m.