Triple
T12443609
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mpondo Kingdom |
E297339
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Pondoland |
E1000687
|
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: Pondoland | Statement: [Mpondo Kingdom, locatedIn, Pondoland]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pondoland Context triple: [Mpondo Kingdom, locatedIn, Pondoland]
-
A.
Pondoland
chosen
Pondoland is a historical coastal region in South Africa, traditionally inhabited and ruled by the Mpondo people.
-
B.
Indian Pond
Indian Pond is a man-made reservoir in Maine created by the impoundment of the West Branch Penobscot River, primarily used for hydroelectric power generation and recreation.
-
C.
Prickend Pond
Prickend Pond is a notable historic village pond and local beauty spot in Chislehurst, in the London Borough of Bromley.
-
D.
Lotus Pond
Lotus Pond is a scenic lake and popular tourist attraction in Kaohsiung, Taiwan, known for its temples, pagodas, and lotus-covered waters.
-
E.
Lotus Pond
Lotus Pond is a serene water feature within the Mahabodhi Temple complex at Bodh Gaya, traditionally associated with the Buddha’s enlightenment and used as a place for reflection and meditation.
- 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_69d6ada166c48190b902972cd2408fa3 |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d94d8fd9848190a83410353d88ea8d |
completed | April 10, 2026, 7:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f684d254888190a22453aede711491 |
completed | May 2, 2026, 11:12 p.m. |
Created at: April 8, 2026, 9:55 p.m.