Triple
T1629535
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Canton Tower |
E35224
|
entity |
| Predicate | wasWorldsTallestTowerFrom |
P1276
|
FINISHED |
| Object | 2009 |
—
|
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: 2009 | Statement: [Canton Tower, wasWorldsTallestTowerFrom, 2009]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasWorldsTallestTowerFrom Context triple: [Canton Tower, wasWorldsTallestTowerFrom, 2009]
-
A.
formerTallestBuildingInTheWorld
Indicates that a building once held, but no longer holds, the record for being the tallest building in the world.
-
B.
formerTallestFreeStandingStructureOnLand
Indicates that one entity was, at some time in the past, the tallest free-standing structure on land relative to the other entity or to all comparable structures.
-
C.
heldTallestStructureTitleFrom
chosen
Indicates that an entity held the title of being the tallest structure for a specified time period starting from a given point.
-
D.
heldTallestStructureTitleUntil
Indicates that one structure held the title of being the tallest in a given context up to and including a specified end time.
-
E.
towerName
Indicates the specific name assigned to a tower in the relationship.
- 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_69a886036bc081909ff5de16dbe5e8ea |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a9431af5ac8190893133f1ae490142 |
completed | March 5, 2026, 8:47 a.m. |
| PD | Predicate disambiguation | batch_69a907c91c888190b6ed295c1a2e0977 |
completed | March 5, 2026, 4:34 a.m. |
Created at: March 4, 2026, 7:28 p.m.