Triple
T9367710
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Father McKenzie |
E225446
|
entity |
| Predicate | performsActionInLyrics |
P88174
|
FINISHED |
| Object | darning his socks |
—
|
LITERAL 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: darning his socks | Statement: [Father McKenzie, performsActionInLyrics, darning his socks]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: performsActionInLyrics Context triple: [Father McKenzie, performsActionInLyrics, darning his socks]
-
A.
scriptUsedInLyrics
Indicates that a particular writing system or script is used to write or represent the lyrics of a song or musical work.
-
B.
hasLyricsIn
Indicates that the lyrics of a work are written or available in a specified language.
-
C.
lyricSetting
Indicates that one entity serves as the text or lyrics that are set to music or otherwise musically realized by another entity.
-
D.
hasLyricCharacter
Indicates that a musical work or song includes a specific character or persona within its lyrics.
-
E.
regulatesLyrics
Indicates that one entity exercises control or governance over the content, use, or distribution of another entity’s lyrics.
- F. None of above. chosen
Provenance (4 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_69ca842cbddc819099d71ecec48cf9e5 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd507f9ed8819092967b204faa4408 |
completed | April 1, 2026, 5:06 p.m. |
| PD | Predicate disambiguation | batch_69cc7a6abb8c81908c7a2f4ee92cc949 |
completed | April 1, 2026, 1:52 a.m. |
| PDg | Predicate description generation | batch_69cc955a38108190b602d1e73725f11b |
completed | April 1, 2026, 3:47 a.m. |
Created at: March 30, 2026, 7:43 p.m.