Triple
T36590442
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Singapore Airlines Cargo |
E902654
|
entity |
| Predicate | usesBellyholdCapacityOf |
P185909
|
FINISHED |
| Object | Singapore Airlines |
—
|
NE NERFINISHED |
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: Singapore Airlines | Statement: [Singapore Airlines Cargo, usesBellyholdCapacityOf, Singapore Airlines]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesBellyholdCapacityOf Context triple: [Singapore Airlines Cargo, usesBellyholdCapacityOf, Singapore Airlines]
-
A.
cargoHoldVolume
Indicates the total internal volume available within a cargo hold for storing goods or materials.
-
B.
externalPayloadCapacity
Indicates the maximum weight of payload that can be carried externally (outside the main body or cargo area) by an entity.
-
C.
cargoHoldWidth
Indicates the width dimension of a cargo hold in a vehicle, vessel, or storage structure.
-
D.
canBeHeldIn
Indicates that one entity is capable of being contained, hosted, or conducted within another entity.
-
E.
hasCargoHold
Indicates that something possesses a dedicated space or compartment for storing or transporting cargo.
- 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_69f76e6592e88190bac4eb00a46e9df9 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7c371931c8190afb1d4dd5157f92c |
completed | May 3, 2026, 9:51 p.m. |
| PD | Predicate disambiguation | batch_69f7c1baf25c8190a78dd54a400d2c50 |
completed | May 3, 2026, 9:44 p.m. |
| PDg | Predicate description generation | batch_69f7c3705b5c81908c84004543a71c07 |
completed | May 3, 2026, 9:51 p.m. |
Created at: May 3, 2026, 4:11 p.m.