Triple
T18912958
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kumar Sangakkara |
E462650
|
entity |
| Predicate | playedForTeam |
P2168
|
FINISHED |
| Object | Wayamba |
—
|
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: Wayamba | Statement: [Kumar Sangakkara, playedForTeam, Wayamba]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wayamba Context triple: [Kumar Sangakkara, playedForTeam, Wayamba]
-
A.
Wayamba
chosen
Wayamba is a Sri Lankan provincial cricket team that competes in the country’s domestic cricket tournaments.
-
B.
Yenda
Yenda is a small rural town in the Riverina region of New South Wales, Australia, known for its agricultural production, particularly viticulture and horticulture.
-
C.
Wiluna
Wiluna is a remote outback town in Western Australia known historically as a gold mining center and as a gateway to desert tracks such as the Canning Stock Route.
-
D.
Wondo
Wondo is the nickname of Chris Wondolowski, a prolific American soccer forward best known for his record-breaking goal-scoring career in Major League Soccer with the San Jose Earthquakes.
-
E.
Umbakumba
Umbakumba is a small Indigenous community and settlement located on Groote Eylandt in the Gulf of Carpentaria, Northern Territory, Australia.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8dcfdbbb881909964fa5a75bd0b48 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5c624516c81909e6bf04707d3c71c |
completed | April 20, 2026, 6:22 a.m. |
Created at: April 10, 2026, 11:58 a.m.