Triple
T25313992
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lion of Lucerne |
E634681
|
entity |
| Predicate | executingSculptor |
P24128
|
FINISHED |
| Object | Lukas Ahorn |
—
|
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: Lukas Ahorn | Statement: [Lion of Lucerne, executingSculptor, Lukas Ahorn]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: executingSculptor Context triple: [Lion of Lucerne, executingSculptor, Lukas Ahorn]
-
A.
hasSculptor
chosen
Indicates that one entity serves as the sculptor (creator of a sculpture) of another entity.
-
B.
currentVersionSculptor
Indicates that a given sculptor entity represents the current or most up-to-date version in a sequence or set of sculptor-related versions.
-
C.
sculpts
Indicates that one entity creates or shapes another entity by carving or modeling a material into a desired form.
-
D.
assistantSculptor
Indicates a relationship where one entity serves as an assistant to another entity in the role or activity of sculpting.
-
E.
usesSculptureFor
Indicates that one entity employs or utilizes a sculpture for a particular purpose, function, or activity.
- 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_69e75a9847c08190bb02990d06d5ffb7 |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f49686fcf081908e2ce81665f1c5ea |
completed | May 1, 2026, 12:03 p.m. |
| PD | Predicate disambiguation | batch_69f4806d93dc8190b9dff4c63186faff |
completed | May 1, 2026, 10:29 a.m. |
Created at: April 21, 2026, 1:27 p.m.