Triple
T1645497
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Berlin TV Tower |
E35571
|
entity |
| Predicate | panoramicViewOf |
P17987
|
FINISHED |
| Object | central Berlin |
—
|
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: central Berlin | Statement: [Berlin TV Tower, panoramicViewOf, central Berlin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: panoramicViewOf Context triple: [Berlin TV Tower, panoramicViewOf, central Berlin]
-
A.
viewOver
chosen
Indicates that one entity has a visual perspective overlooking or facing another entity, typically providing a vantage point onto it.
-
B.
perspectiveOf
Indicates that something is expressed, depicted, or understood from the viewpoint or standpoint of a particular entity.
-
C.
hasScenicViewOf
Indicates that one entity offers a visually appealing or picturesque view of another entity.
-
D.
viewedEarthAs
Indicates perceiving or regarding Earth in a particular way, often reflecting an attitude, interpretation, or conceptual perspective toward the planet.
-
E.
visionOf
Indicates that one entity is a visual representation, image, or depiction of another entity.
- 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_69a88604618c81908b41f6429c431eb6 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a919306fd48190a245fc95e0e759d9 |
completed | March 5, 2026, 5:48 a.m. |
| PD | Predicate disambiguation | batch_69a907cc9d348190b76b0d3f596e5a81 |
completed | March 5, 2026, 4:34 a.m. |
Created at: March 4, 2026, 7:28 p.m.