Triple
T11261189
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Matsapha Airport |
E266562
|
entity |
| Predicate | serves |
P98
|
FINISHED |
| Object | Manzini |
E397182
|
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: Manzini | Statement: [Matsapha Airport, serves, Manzini]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Manzini Context triple: [Matsapha Airport, serves, Manzini]
-
A.
Manzini
chosen
Manzini is a major city in Eswatini that serves as an important commercial and transport hub of the country.
-
B.
Mbabane
Mbabane is the largest city and administrative center of Eswatini, located in the country's western highlands.
-
C.
Sesheke
Sesheke is a significant town in western Zambia’s Barotseland region, located near the Zambezi River and the border with Namibia.
-
D.
Lobamba
Lobamba is the traditional and legislative capital of Eswatini, serving as the seat of the Swazi monarchy and key national institutions.
-
E.
Masindi
Masindi is a town in western Uganda that serves as a key gateway and service center for visitors to Murchison Falls National Park.
- 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_69d6aac7953c8190b82caf9d7640fdf9 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e94c066c8190be1e032eb328e5fe |
completed | April 9, 2026, 6 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e4f410cb508190bb0ceab51075eec5 |
completed | April 19, 2026, 3:26 p.m. |
Created at: April 8, 2026, 9:31 p.m.