Triple
T33849294
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | A Portrait of Merle Haggard |
E867570
|
entity |
| Predicate | includesSongwritingBy |
P70268
|
FINISHED |
| Object | Merle Haggard |
E49579
|
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: Merle Haggard | Statement: [A Portrait of Merle Haggard, includesSongwritingBy, Merle Haggard]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: includesSongwritingBy Context triple: [A Portrait of Merle Haggard, includesSongwritingBy, Merle Haggard]
-
A.
containsSongWrittenBy
chosen
Indicates that an entity (such as an album, playlist, or collection) includes at least one song that was written by a specified creator or songwriter.
-
B.
originalSongwritersAlsoInclude
Indicates that, in addition to the primary credited songwriters, there are other individuals who also contributed to writing the original song.
-
C.
showcasesSongwriting
Indicates that something highlights or demonstrates the quality, style, or skill of a particular songwriting effort.
-
D.
coSongwriter
Indicates that two or more entities collaborated in writing the same song.
-
E.
songwritingCredit
Indicates that one entity is credited as a songwriter or co-songwriter for a musical work associated with another entity.
- F. None of above.
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_69f349937b648190a34ada70f6a2b534 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_6a036fb4650c81908df9b9ec8ed8594b |
completed | May 12, 2026, 6:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a36c1ad0fac8190b84b6dbffd827eb1 |
completed | June 20, 2026, 4:37 p.m. |
| PD | Predicate disambiguation | batch_6a036f64dc648190a31cf944d3ea0f7d |
completed | May 12, 2026, 6:20 p.m. |
Created at: May 1, 2026, 1:47 a.m.