Triple
T27774106
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Main Deck (Tokyo Tower) |
E699137
|
entity |
| Predicate | relativePositionInTower |
P27751
|
FINISHED |
| Object | below the Top Deck (Tokyo Tower) |
—
|
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: below the Top Deck (Tokyo Tower) | Statement: [Main Deck (Tokyo Tower), relativePositionInTower, below the Top Deck (Tokyo Tower)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relativePositionInTower Context triple: [Main Deck (Tokyo Tower), relativePositionInTower, below the Top Deck (Tokyo Tower)]
-
A.
positionRelativeToTower
chosen
Indicates the spatial relationship or placement of an entity with respect to a specified tower.
-
B.
positionRelativeToBuilding
Indicates the spatial relationship of an entity’s location with respect to a specific building (e.g., in front of, behind, adjacent to, on top of).
-
C.
hasTowerPosition
Indicates that an entity occupies or is assigned a specific position or location within a tower.
-
D.
elevationRelativeToFloor
Indicates the vertical distance or height of an entity measured relative to the floor level.
-
E.
positionRelativeToPower
Indicates the spatial or structural placement of one entity in relation to a power source, power line, or power-related infrastructure.
- 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_69ef6a4b5a9081909c9111396c2be3d2 |
completed | April 27, 2026, 1:53 p.m. |
| NER | Named-entity recognition | batch_69ff8cecbf048190860b9f72b8753f5c |
completed | May 9, 2026, 7:37 p.m. |
| PD | Predicate disambiguation | batch_69ff8c4c39dc8190b5bf35adc1bae7c6 |
completed | May 9, 2026, 7:34 p.m. |
Created at: April 27, 2026, 5:04 p.m.