Triple
T28587518
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Schönheitengalerie |
E723549
|
entity |
| Predicate | hasNotableSitter |
P199501
|
FINISHED |
| Object | Lola Montez |
—
|
NE NERFINISHED |
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: Lola Montez | Statement: [Schönheitengalerie, hasNotableSitter, Lola Montez]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNotableSitter Context triple: [Schönheitengalerie, hasNotableSitter, Lola Montez]
-
A.
sitterOf
Indicates that one entity serves as a caretaker or babysitter responsible for looking after another entity.
-
B.
sitterIn
Indicates that one entity is acting as a sitter (e.g., babysitter, pet sitter, house sitter) for another entity or at a particular place.
-
C.
sitter
Indicates that one entity is serving as a caretaker or guardian, typically watching over or looking after another entity.
-
D.
hasParentalUnit
Indicates that an entity has a parent or guardian that serves as its primary caregiving or parental figure.
-
E.
sitterStatus
Indicates the current role, availability, or engagement state of a sitter in relation to a sitting arrangement or service.
- F. None of above. chosen
Provenance (4 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_69f01d7f92e481909847f5f3f3174a89 |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_69ff3fb2318c81908a46c2f513608935 |
completed | May 9, 2026, 2:07 p.m. |
| PD | Predicate disambiguation | batch_69ff3e96dcc48190819f6204680d84aa |
completed | May 9, 2026, 2:03 p.m. |
| PDg | Predicate description generation | batch_69ff3fb151008190bf8a90f9f1c5f0c8 |
completed | May 9, 2026, 2:07 p.m. |
Created at: April 28, 2026, 4:18 a.m.