Triple
T23850491
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | My Immortal |
E592147
|
entity |
| Predicate | originalDemoRecordingYear |
P130159
|
FINISHED |
| Object | 1990s |
—
|
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: 1990s | Statement: [My Immortal, originalDemoRecordingYear, 1990s]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originalDemoRecordingYear Context triple: [My Immortal, originalDemoRecordingYear, 1990s]
-
A.
recordingYear
Indicates the specific calendar year in which something (such as audio, video, or data) was recorded.
-
B.
originalDemoDate
chosen
Indicates the date on which something (such as a product, feature, or work) was first demonstrated in its original form.
-
C.
recordingReleaseYear
Indicates the calendar year in which a particular recording was first released to the public.
-
D.
bestKnownRecordingYear
Indicates the year in which the most notable or widely recognized recording of something was made or released.
-
E.
reRecordedReleaseYear
Indicates the year in which an existing work was recorded again and that re-recorded version was released.
- 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_69e25d221d908190b9b502ad31e66a3f |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1c986f7e08190a6d361423946ff05 |
completed | April 29, 2026, 9:04 a.m. |
| PD | Predicate disambiguation | batch_69f1614612b481908c45d99e588882f9 |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 8:11 p.m.