Triple
T24453900
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Palisadoes Airport |
E616623
|
entity |
| Predicate | wasArrivalPointOf |
P1522
|
FINISHED |
| Object | Haile Selassie I |
—
|
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: Haile Selassie I | Statement: [Palisadoes Airport, wasArrivalPointOf, Haile Selassie I]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasArrivalPointOf Context triple: [Palisadoes Airport, wasArrivalPointOf, Haile Selassie I]
-
A.
isMainArrivalPointFor
Indicates that a location serves as the primary arrival point for a given entity or flow of entities.
-
B.
placeOfArrival
chosen
Indicates the location at which an entity or person arrives at the end of a journey, movement, or transfer.
-
C.
wasTransitPointOn
Indicates that something served as an intermediate stop or passage location along a specified route, journey, or transport path.
-
D.
hasArrivalAirport
Indicates the airport at which a journey, flight, or trip concludes or arrives.
-
E.
hasArrivalArea
Indicates that an entity is associated with a specific area designated for arrivals, such as where incoming people or items first enter or are received.
- 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_69e2d7ef9fe08190a0613908758b4e86 |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f298c4f1d881909d9119fec74afe53 |
completed | April 29, 2026, 11:48 p.m. |
| PD | Predicate disambiguation | batch_69f287d3237c819099559c00f83131d8 |
completed | April 29, 2026, 10:36 p.m. |
Created at: April 18, 2026, 2:18 a.m.