Triple
T34948869
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Angel of the Morning |
E1007927
|
entity |
| Predicate | firstHitVersionBy |
P206750
|
FINISHED |
| Object | Merrilee Rush |
E1860850
|
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: Merrilee Rush | Statement: [Angel of the Morning, firstHitVersionBy, Merrilee Rush]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstHitVersionBy Context triple: [Angel of the Morning, firstHitVersionBy, Merrilee Rush]
-
A.
firstMajorVersionBy
Indicates that one entity is the earliest or initial major version created or released by another entity.
-
B.
firstReleaseVersion
Indicates the specific version identifier associated with the initial public release of something.
-
C.
hasFirstVersion
Indicates that one entity is the earliest or original version in a sequence of versions related to another entity.
-
D.
firstFullVersionReference
Indicates that one entity serves as the initial complete or fully realized version to which another entity refers or is linked.
-
E.
principalVersionFor
Indicates a relationship where one version of an entity is designated as the primary or authoritative version for another related entity.
- F. None of above. chosen
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_69f76dc5d4308190b77553ee07b1ede6 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_6a037c92f03c8190ae2751270b195423 |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a5a5ad1cf488190bb2e70306892bb3e |
completed | July 17, 2026, 4:39 p.m. |
| PD | Predicate disambiguation | batch_6a0379ff1ba081908eda86acefcf69fb |
completed | May 12, 2026, 7:05 p.m. |
| PDg | Predicate description generation | batch_6a037c82179081908325a59b8539b3a8 |
completed | May 12, 2026, 7:16 p.m. |
Created at: May 3, 2026, 4 p.m.