Triple
T3219695
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Heinrich Hoffmann |
E67479
|
entity |
| Predicate | ran |
P42738
|
FINISHED |
| Object | photo studio in Munich |
—
|
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: photo studio in Munich | Statement: [Heinrich Hoffmann, ran, photo studio in Munich]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ran Context triple: [Heinrich Hoffmann, ran, photo studio in Munich]
-
A.
runs
chosen
Indicates that an entity moves swiftly on foot, typically using its legs in a continuous, rapid motion.
-
B.
rukus
Indicates that an entity is associated with or participates in a disturbance, commotion, or noisy disruptive event involving another entity.
-
C.
range
Indicates that a value, property, or effect extends between specified limits or over a specified interval or scope.
-
D.
laps
Indicates that one entity moves around another entity or a course, typically completing a circuit or overtaking it.
-
E.
radical
Indicates that an entity holds or is associated with extreme, fundamental, or revolutionary views, changes, or characteristics relative to a norm.
- 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_69ad858b8adc8190ad989712c87a476b |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69adab0ef2c88190ab89e3217438a2bf |
completed | March 8, 2026, 4:59 p.m. |
| PD | Predicate disambiguation | batch_69ad9e0bb6c48190a0659c67d40ee37c |
completed | March 8, 2026, 4:04 p.m. |
Created at: March 8, 2026, 3:08 p.m.