Triple

T13365963
Position Surface form Disambiguated ID Type / Status
Subject Steve Cropper E318937 entity
Predicate wroteOrCoWrote P47055 FINISHED
Object Knock on Wood E894623 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: Knock on Wood | Statement: [Steve Cropper, wroteOrCoWrote, Knock on Wood]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Knock on Wood
Context triple: [Steve Cropper, wroteOrCoWrote, Knock on Wood]
  • A. Knock on Wood
    Knock on Wood is a 1954 comedy film starring Danny Kaye as a ventriloquist entangled in international espionage and romantic misadventures.
  • B. Knock on Wood chosen
    "Knock on Wood" is a popular song best known in its 1966 soul original by Eddie Floyd and its numerous later cover versions across soul, disco, and pop music.
  • C. Wishing Well
    "Wishing Well" is a posthumously released emo-rap song by Juice WRLD that reflects on his struggles with addiction and mental health.
  • D. Wishing Well
    "Wishing Well" is a song by the English rock band Free, best known for its blues-rock style and Paul Rodgers' powerful vocals.
  • E. Wishing Well
    Wishing Well is a popular underground pool feature in Luray Caverns where visitors toss coins while making wishes, with the collected money often donated to charity.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d806b7bbac8190b85278c87fa7aff3 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69dbae47e99081909d8b5dba97a11988 completed April 12, 2026, 2:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69f730687e548190ab1504d43f250e09 completed May 3, 2026, 11:24 a.m.
Created at: April 9, 2026, 9:32 p.m.