Triple
T18570724
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aravinda de Silva |
E453865
|
entity |
| Predicate | testCapNumberForSriLanka |
P132615
|
FINISHED |
| Object | 28 |
—
|
LITERAL 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: 28 | Statement: [Aravinda de Silva, testCapNumberForSriLanka, 28]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: testCapNumberForSriLanka Context triple: [Aravinda de Silva, testCapNumberForSriLanka, 28]
-
A.
testCapNumberForWestIndies
Indicates the assigned cap number used to identify a player who has represented the West Indies cricket team.
-
B.
t20iCapNumber
Indicates that an entity has a specific cap number (e.g., a player’s official cap or appearance number) assigned to it.
-
C.
smsCapacity
Indicates the maximum number of SMS messages that can be stored, sent, or handled within a given system or context.
-
D.
testCaps
Indicates that an entity is being tested or evaluated for its capacity, capability, or limits in relation to another entity or context.
-
E.
hasInternationalCapsFor
Indicates that an individual has made official appearances (caps) for a specified national team in international competition.
- F. None of above. chosen
Provenance (4 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_69d8d38974308190a9174430ef256b73 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e53b01331c8190bec3aba40358a843 |
completed | April 19, 2026, 8:28 p.m. |
| PD | Predicate disambiguation | batch_69e478c16e0c8190b03966aa23c395a6 |
completed | April 19, 2026, 6:40 a.m. |
| PDg | Predicate description generation | batch_69e484121cd48190bf583b4c94636a30 |
completed | April 19, 2026, 7:28 a.m. |
Created at: April 10, 2026, 11:43 a.m.