Triple
T15736046
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Port Elizabeth |
E381472
|
entity |
| Predicate | governingCountryCapital |
P204
|
FINISHED |
| Object | Kingstown |
E71861
|
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: Kingstown | Statement: [Port Elizabeth, governingCountryCapital, Kingstown]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kingstown Context triple: [Port Elizabeth, governingCountryCapital, Kingstown]
-
A.
Kingstown
Kingstown is the former English name of the coastal Irish town now known as Dún Laoghaire, a major port and suburb of Dublin.
-
B.
Kingstown
chosen
Kingstown is the main commercial and administrative center of Saint Vincent and the Grenadines, located on the southwestern coast of the island of Saint Vincent.
-
C.
Kingston
Kingston is a borough in northeastern Pennsylvania, United States, situated along the Susquehanna River near the city of Wilkes-Barre.
-
D.
Kingston
Kingston is a small unincorporated community and historic mining town located in central Nevada, United States.
-
E.
Kingston
Kingston is a residential suburb located on Portsea Island in the city of Portsmouth, England.
- 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_69d86d9cdb648190bf3171be0bd7d872 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e04fd586a88190aa1b1b88368d386f |
completed | April 16, 2026, 2:56 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffb03539c081908b5df46bb810b949 |
completed | May 9, 2026, 10:07 p.m. |
Created at: April 10, 2026, 4:46 a.m.