Triple
T1743901
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Obelisco de Buenos Aires |
E38292
|
entity |
| Predicate | hasViewingWindows |
P8656
|
FINISHED |
| Object | small windows near the top |
—
|
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: small windows near the top | Statement: [Obelisco de Buenos Aires, hasViewingWindows, small windows near the top]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasViewingWindows Context triple: [Obelisco de Buenos Aires, hasViewingWindows, small windows near the top]
-
A.
windowType
chosen
Indicates the specific kind or category of window associated with an entity.
-
B.
hasViewingSide
Indicates that one entity serves as the side or surface of another entity that is intended to be viewed or observed.
-
C.
hasViewingPlatform
Indicates that an entity includes or is equipped with a designated platform or area intended for viewing or observing something.
-
D.
hasView
Indicates that one entity provides a visual perspective or outlook onto another entity or scene.
-
E.
viewOver
Indicates that one entity has a visual perspective overlooking or facing another entity, typically providing a vantage point onto it.
- 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_69a8862b01a48190ab47209063af82d9 |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69ab630e7d008190a8c673665d9672bb |
completed | March 6, 2026, 11:28 p.m. |
| PD | Predicate disambiguation | batch_69aa61c5a18481909bc49e0c54d64314 |
completed | March 6, 2026, 5:10 a.m. |
Created at: March 4, 2026, 7:31 p.m.