Triple
T31445247
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Living with the Land rainforest scene |
E802168
|
entity |
| Predicate | originalAttractionName |
P202832
|
FINISHED |
| Object | Listen to the Land |
—
|
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: Listen to the Land | Statement: [Living with the Land rainforest scene, originalAttractionName, Listen to the Land]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originalAttractionName Context triple: [Living with the Land rainforest scene, originalAttractionName, Listen to the Land]
-
A.
previousAttraction
Indicates that one entity was formerly an attraction or point of interest associated with another entity in the past.
-
B.
originalParkName
Indicates the relationship where a park is associated with its original or former official name.
-
C.
recordAttraction
Indicates that an instance of an attraction (e.g., interest or appeal) is documented or logged as a record in relation to another entity.
-
D.
previousAttractionType
Indicates that an entity previously had a different attraction type or category before its current one.
-
E.
themeParkAttraction
Indicates that something is an attraction or ride located within a theme park.
- F. None of above. chosen
Provenance (4 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_69f348c5a6bc819092a557e95438976f |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_6a00c3362dcc819096e49b882709fddd |
completed | May 10, 2026, 5:41 p.m. |
| PD | Predicate disambiguation | batch_6a00c2e5cdd88190a5f2d0f6a843cd56 |
completed | May 10, 2026, 5:39 p.m. |
| PDg | Predicate description generation | batch_6a00c3355498819088253d5e5c17267f |
completed | May 10, 2026, 5:41 p.m. |
Created at: April 30, 2026, 9:08 p.m.