Triple
T11075668
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Serena Hotels development in Asia and Africa |
E261857
|
entity |
| Predicate | experienceTheme |
P27612
|
FINISHED |
| Object | safari and wildlife experiences |
—
|
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: safari and wildlife experiences | Statement: [Serena Hotels development in Asia and Africa, experienceTheme, safari and wildlife experiences]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: experienceTheme Context triple: [Serena Hotels development in Asia and Africa, experienceTheme, safari and wildlife experiences]
-
A.
experienceFeature
Indicates that an entity undergoes, encounters, or makes use of a particular feature.
-
B.
experienceStyle
Indicates that one entity has or is associated with a particular manner, approach, or style in which an experience is delivered or undergone.
-
C.
providesExperienceOf
Indicates that one entity enables or delivers the experience of another entity to someone or something.
-
D.
experiences
Indicates that an entity undergoes, feels, or is affected by a particular event, state, or condition.
-
E.
tourismTheme
chosen
Indicates the main subject or focus of a tourism-related activity, service, or destination (such as cultural, adventure, or eco-tourism).
- 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_69d6aa9983c08190b0ef61603b69feac |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d7994efb608190a81bc8c4d16ddbd0 |
completed | April 9, 2026, 12:19 p.m. |
| PD | Predicate disambiguation | batch_69d74415403c81909778bcd829e8832e |
completed | April 9, 2026, 6:15 a.m. |
Created at: April 8, 2026, 9:26 p.m.