Triple
T16985160
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Runway 06/24 |
E412045
|
entity |
| Predicate | hasICAOAirport |
P419
|
FINISHED |
| Object | FALA |
E299488
|
NE 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: FALA | Statement: [Runway 06/24, hasICAOAirport, FALA]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: FALA Context triple: [Runway 06/24, hasICAOAirport, FALA]
-
A.
FALA
chosen
FALA is the ICAO airport code for Lanseria International Airport, a major privately owned international airport serving the Johannesburg region in South Africa.
-
B.
FALY
FALY is the ICAO airport code assigned to Ladysmith Airport in South Africa.
-
C.
FALE
FALE is the ICAO airport code assigned to King Shaka International Airport in Durban, South Africa.
-
D.
Fale
Fale is a village settlement on the atoll of Fakaofo in Tokelau, a New Zealand-administered territory in the South Pacific.
-
E.
Falalop
Falalop is a small inhabited island within Ulithi Atoll in the Federated States of Micronesia, known for hosting an airfield and serving as one of the atoll’s main population centers.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d886ca8f348190812768ea8d5055ce |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d18af95c8190a25ef0614e1a17f3 |
completed | April 18, 2026, 6:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00dc1109a081908890bbd5958c76c2 |
completed | May 10, 2026, 7:27 p.m. |
Created at: April 10, 2026, 5:32 a.m.