Triple
T37168818
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Erawan Shrine |
E920856
|
entity |
| Predicate | hasTypeOfOffering |
P34857
|
FINISHED |
| Object | marigold garlands |
—
|
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: marigold garlands | Statement: [Erawan Shrine, hasTypeOfOffering, marigold garlands]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTypeOfOffering Context triple: [Erawan Shrine, hasTypeOfOffering, marigold garlands]
-
A.
hasOffering
Indicates that one entity provides, presents, or makes available an offering (such as a product, service, or item) to another entity or context.
-
B.
offeringType
chosen
Indicates the category or nature of what is being offered in a transaction or interaction (e.g., product, service, or other type of offering).
-
C.
isOfferedBy
Indicates that a service, product, or opportunity is provided or made available by a particular entity.
-
D.
providesOfferingsTo
Indicates that one entity supplies or presents offerings, such as goods, services, or benefits, to another entity.
-
E.
usesOffering
Indicates that one entity makes use of, applies, or relies on a particular offering provided by another entity.
- 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_69f76ea16f288190b445aa1604d996f4 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69ffc516d1908190b475f5a6156b0ca8 |
completed | May 9, 2026, 11:36 p.m. |
| PD | Predicate disambiguation | batch_69ffc4a946e08190b3535a5dc15ac484 |
completed | May 9, 2026, 11:35 p.m. |
Created at: May 3, 2026, 4:15 p.m.