Triple
T22420292
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pitadeniya |
E554226
|
entity |
| Predicate | mainEntryPointFor |
P26093
|
FINISHED |
| Object | visitors to Sinharaja Forest Reserve |
—
|
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: visitors to Sinharaja Forest Reserve | Statement: [Pitadeniya, mainEntryPointFor, visitors to Sinharaja Forest Reserve]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mainEntryPointFor Context triple: [Pitadeniya, mainEntryPointFor, visitors to Sinharaja Forest Reserve]
-
A.
mainStartingPoint
Indicates the primary location or position from which an event, process, or path begins.
-
B.
entryPointFor
chosen
Indicates that one entity serves as the access or starting location through which another entity is entered, initiated, or reached.
-
C.
mainEntranceOn
Indicates that the primary entrance of one entity is located on or faces toward another entity, such as a particular side, street, or boundary.
-
D.
programEntryMethod
Indicates that a method serves as the starting point or main entry method for executing a program or component.
-
E.
mainEntranceLocation
Indicates the location where the primary or main entrance of an entity is situated.
- 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_69e11e4f2d0c819091aa3558ea2ee630 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f1594a58508190b41fd16c8de5f8b4 |
completed | April 29, 2026, 1:05 a.m. |
| PD | Predicate disambiguation | batch_69e8989495bc81909d2699fce5992e28 |
completed | April 22, 2026, 9:44 a.m. |
Created at: April 16, 2026, 8:46 p.m.