Triple
T34394752
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Singapore Airlines passengers |
E882799
|
entity |
| Predicate | departFrom |
P1521
|
FINISHED |
| Object | Singapore Changi Airport |
—
|
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 Changi Airport | Statement: [Singapore Airlines passengers, departFrom, Singapore Changi Airport]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: departFrom Context triple: [Singapore Airlines passengers, departFrom, Singapore Changi Airport]
-
A.
departsFrom
Indicates that an entity (such as a vehicle, person, or process) begins its movement, journey, or operation starting from a specified location or point of origin.
-
B.
placeOfDeparture
chosen
Indicates the location from which an entity, such as a person or vehicle, begins its journey or movement.
-
C.
mayDepartFrom
Indicates that an entity is permitted or authorized to leave or start from a specified location or point of origin.
-
D.
departureFromSeries
Indicates that an entity stops being part of, or exits from, a particular series or sequence.
-
E.
hasDepartureTo
Indicates that a departure event originates from one place and is directed toward a specific destination.
- 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_69f349c1304081909331872829e38106 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f71c35327c8190884f1bfe12bd2cd7 |
completed | May 3, 2026, 9:58 a.m. |
| PD | Predicate disambiguation | batch_69f71822d0e88190ac9731c7ae5a4def |
completed | May 3, 2026, 9:40 a.m. |
Created at: May 1, 2026, 1:59 a.m.