Triple
T6582418
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Murnau – Street with Women |
E157328
|
entity |
| Predicate | approximate creation date |
P13262
|
FINISHED |
| Object | circa 1908 |
—
|
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: circa 1908 | Statement: [Murnau – Street with Women, approximate creation date, circa 1908]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: approximate creation date Context triple: [Murnau – Street with Women, approximate creation date, circa 1908]
-
A.
estimatedYearOfCreation
chosen
Indicates the year in which something is believed or approximated to have been created, rather than a precisely known creation year.
-
B.
dateApproximate
Indicates that the associated date is not exact but estimated or approximate rather than precisely known.
-
C.
approximateStartYear
Indicates that the associated year value represents an estimated or imprecise starting year for an event, state, or relationship rather than an exact one.
-
D.
approximateYearOfCompletion
Indicates the estimated calendar year in which something was completed, rather than an exact or confirmed year.
-
E.
initialReleaseApprox
Indicates that an entity’s first release or debut occurred around an estimated or approximate point in time rather than on a precisely known date.
- 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_69c6882b3a108190b3a9eb343ae4162c |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6c07cdf048190945ca5810fb1de88 |
completed | March 27, 2026, 5:38 p.m. |
| PD | Predicate disambiguation | batch_69c6acfb462481909cb7aff5af4bca9d |
completed | March 27, 2026, 4:14 p.m. |
Created at: March 27, 2026, 1:54 p.m.