Triple
T9233117
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Philadelphia City Hall |
E221869
|
entity |
| Predicate | wasTallestBuildingOfType |
P87709
|
FINISHED |
| Object | masonry building |
—
|
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: masonry building | Statement: [Philadelphia City Hall, wasTallestBuildingOfType, masonry building]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasTallestBuildingOfType Context triple: [Philadelphia City Hall, wasTallestBuildingOfType, masonry building]
-
A.
wasTallestStructureIn
Indicates that one structure held the status of being the tallest within a specified place or during a specified time period.
-
B.
tallestBuildingIn
Indicates that one entity is the tallest building located within the area or region specified by the other entity.
-
C.
isTallestStructureIn
Indicates that the subject is the tallest structure located within the specified place or area.
-
D.
formerTallestBuildingInTheWorld
Indicates that a building once held, but no longer holds, the record for being the tallest building in the world.
-
E.
formerTallestBuildingIn
Indicates that a building was once the tallest building within a specified place or region, but no longer holds that status.
- 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_69ca83ed628c8190bc02d641e57f097f |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69ccee1baa3c8190870d1e850ccab1e0 |
completed | April 1, 2026, 10:06 a.m. |
| PD | Predicate disambiguation | batch_69cc7a3daeb481908b0abde3fbc1f1f0 |
completed | April 1, 2026, 1:51 a.m. |
| PDg | Predicate description generation | batch_69cc95597be081908ece2491dd2f0f74 |
completed | April 1, 2026, 3:47 a.m. |
Created at: March 30, 2026, 7:29 p.m.