Triple
T11018827
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pelléas et Mélisande |
E260432
|
entity |
| Predicate | firstCompleteRecordingYear |
P78514
|
FINISHED |
| Object | 1920s |
—
|
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: 1920s | Statement: [Pelléas et Mélisande, firstCompleteRecordingYear, 1920s]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstCompleteRecordingYear Context triple: [Pelléas et Mélisande, firstCompleteRecordingYear, 1920s]
-
A.
firstRecordingDate
Indicates the date on which an entity’s first recording (e.g., audio, video, or similar captured performance) was made.
-
B.
firstCaptureYear
chosen
Indicates the year in which an entity was first captured or recorded as captured.
-
C.
recordStartYear
Indicates the calendar year in which a particular record, entry, or data instance first began or was created.
-
D.
firstCompleterYear
Indicates the calendar or academic year in which an entity first completed a specified program, requirement, or activity.
-
E.
firstSeasonRecorded
Indicates the specific season in which an entity (such as a team, player, or show) was first officially recorded or documented as active.
- 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_69d6aa9687448190b28d353b1b6a610e |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d797a9e8788190a0f45b52bad1bfb5 |
completed | April 9, 2026, 12:12 p.m. |
| PD | Predicate disambiguation | batch_69d72e995e008190bbffb314129ed0cd |
completed | April 9, 2026, 4:44 a.m. |
Created at: April 8, 2026, 9:25 p.m.