Triple
T948376
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Philadelphia City Hall |
E20463
|
entity |
| Predicate | wasTallestBuildingInPhiladelphiaUntil |
P2471
|
FINISHED |
| Object | 1987 |
—
|
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: 1987 | Statement: [Philadelphia City Hall, wasTallestBuildingInPhiladelphiaUntil, 1987]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasTallestBuildingInPhiladelphiaUntil Context triple: [Philadelphia City Hall, wasTallestBuildingInPhiladelphiaUntil, 1987]
-
A.
SearsTowerLaterRenamed
Indicates that something originally known as the Sears Tower was later given a different official name.
-
B.
formerTallestBuildingInTheWorld
Indicates that a building once held, but no longer holds, the record for being the tallest building in the world.
-
C.
usedAsCityHallUntil
Indicates that a building or location functioned as the city hall up to a specified end date or time period.
-
D.
tallestBuildingIn
chosen
Indicates that one entity is the tallest building located within the area or region specified by the other entity.
-
E.
One World Trade CenterInstanceOf
Indicates that One World Trade Center belongs to or is classified as a specific type or class of thing (its general category).
- 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_69a493b0f2fc81908cd227480a5356a1 |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4b3bf9bb88190a79b2db698613a8d |
completed | March 1, 2026, 9:46 p.m. |
| PD | Predicate disambiguation | batch_69a4b29f05f481908814bd11f235e9d0 |
completed | March 1, 2026, 9:41 p.m. |
Created at: March 1, 2026, 7:40 p.m.