Triple
T25331156
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mohammad Shami |
E635154
|
entity |
| Predicate | TestDebutVenue |
P26336
|
FINISHED |
| Object | Eden Gardens, Kolkata |
—
|
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: Eden Gardens, Kolkata | Statement: [Mohammad Shami, TestDebutVenue, Eden Gardens, Kolkata]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: TestDebutVenue Context triple: [Mohammad Shami, TestDebutVenue, Eden Gardens, Kolkata]
-
A.
testDebutVenue
chosen
Indicates the venue or location where an entity (such as a person, product, or performance) made its first test appearance or trial debut.
-
B.
testDebut
Indicates the event or context in which an entity (such as a product, feature, or work) is first introduced or used in a testing environment.
-
C.
firstTestVenue
Indicates the venue where something (such as an event, performance, or test) was held or conducted for the first time.
-
D.
testDebutFor
Indicates that an entity makes its first appearance or performance in a particular test event, context, or setting.
-
E.
startVenue
Indicates the venue or location where an event, journey, or activity begins.
- F. None of above.
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_69e75a9908108190a95427a97020632a |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f497c5f86c81908cf1ce29669bafbe |
completed | May 1, 2026, 12:08 p.m. |
| PD | Predicate disambiguation | batch_69f4683472ec8190a483b3b8afe71720 |
completed | May 1, 2026, 8:45 a.m. |
Created at: April 21, 2026, 1:30 p.m.