Triple
T28466478
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Palacio Barolo |
E720305
|
entity |
| Predicate | formerTallestBuildingStatusPeriod |
P195533
|
FINISHED |
| Object | early 1920s |
—
|
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: early 1920s | Statement: [Palacio Barolo, formerTallestBuildingStatusPeriod, early 1920s]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formerTallestBuildingStatusPeriod Context triple: [Palacio Barolo, formerTallestBuildingStatusPeriod, early 1920s]
-
A.
formerTallestBuildingIn
Indicates that a building was once the tallest building within a specified place or region, but no longer holds that status.
-
B.
wasTallestBuildingUntilYear
Indicates that a building held the status of being the tallest building up to, but not beyond, a specified year.
-
C.
formerTallestBuildingInTheWorld
Indicates that a building once held, but no longer holds, the record for being the tallest building in the world.
-
D.
wasTallestBuildingFromYear
Indicates that a building held the status of being the tallest building starting from a specified year.
-
E.
heldTallestStructureTitleUntil
Indicates that one structure held the title of being the tallest in a given context up to and including a specified end time.
- 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_69f01a58a67c819097936d9e8da8d6e6 |
completed | April 28, 2026, 2:24 a.m. |
| NER | Named-entity recognition | batch_69fdd92396788190ae1424bc1ae55844 |
completed | May 8, 2026, 12:37 p.m. |
| PD | Predicate disambiguation | batch_69fdd678f40481909a717a2daec83b36 |
completed | May 8, 2026, 12:26 p.m. |
| PDg | Predicate description generation | batch_69fdd922d73c81908ad3faade247ec16 |
completed | May 8, 2026, 12:37 p.m. |
Created at: April 28, 2026, 2:45 a.m.