Triple
T38513944
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dry as a Bone |
E921988
|
entity |
| Predicate | chronologyPreviousRelease |
P22762
|
FINISHED |
| Object | Come on Down |
—
|
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: Come on Down | Statement: [Dry as a Bone, chronologyPreviousRelease, Come on Down]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: chronologyPreviousRelease Context triple: [Dry as a Bone, chronologyPreviousRelease, Come on Down]
-
A.
chronologyPrevious
chosen
Indicates that one event, item, or state occurs directly before another in a chronological sequence.
-
B.
chronologyPreviousWorkOf
Indicates that one work temporally precedes and is part of the earlier sequence in the overall body of another work.
-
C.
followsInReleaseChronology
Indicates that one entity is released after another in a chronological sequence of releases.
-
D.
chronologyPrecedes
Indicates that one event or state occurs earlier in time than another in a chronological sequence.
-
E.
chronologyNextPublicationDate
Indicates that one publication directly follows another in time, specifying the date on which the subsequent publication occurs.
- F. None of above.
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_69f76ea3c5448190aa7002fc1ba3f874 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fec25f0fc48190b87ab1f9cd1eb0de |
completed | May 9, 2026, 5:13 a.m. |
| PD | Predicate disambiguation | batch_69fec079a770819098df7cc3049df954 |
completed | May 9, 2026, 5:04 a.m. |
Created at: May 3, 2026, 4:32 p.m.