Triple
T11329395
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sentosa Island |
E268301
|
entity |
| Predicate | touristArrivals |
P12597
|
FINISHED |
| Object | attracts millions of visitors annually |
—
|
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: attracts millions of visitors annually | Statement: [Sentosa Island, touristArrivals, attracts millions of visitors annually]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: touristArrivals Context triple: [Sentosa Island, touristArrivals, attracts millions of visitors annually]
-
A.
touristArrivalsShareInTerritory
Indicates the proportion of total tourist arrivals that occur within a specific territory relative to a larger reference area or total.
-
B.
touristArrivalsPerYearApprox
chosen
Indicates an approximate count of how many tourists arrive at a place over the course of a year.
-
C.
touristArrivalsRank
Indicates the relative position of a place compared to others based on the number of tourists arriving there.
-
D.
shareTourismFlows
Indicates that two places are connected by or exchange significant tourism flows, such as visitors or tourist traffic, between them.
-
E.
tourismTrend
Indicates how patterns or levels of tourism activity change over time or across locations.
- 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_69d6aacb1f0881908c84a349fd1be047 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e9e330008190b75490efde01dc59 |
completed | April 9, 2026, 6:03 p.m. |
| PD | Predicate disambiguation | batch_69d787afe5a48190b8af1a3e19529641 |
completed | April 9, 2026, 11:04 a.m. |
Created at: April 8, 2026, 9:32 p.m.