Triple
T24862297
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maui road network |
E622183
|
entity |
| Predicate | connectsAttraction |
P107600
|
FINISHED |
| Object | Haleakalā National Park |
—
|
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: Haleakalā National Park | Statement: [Maui road network, connectsAttraction, Haleakalā National Park]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: connectsAttraction Context triple: [Maui road network, connectsAttraction, Haleakalā National Park]
-
A.
relatedAttraction
Indicates that one attraction is associated with or connected to another attraction in some relevant way.
-
B.
connectsTouristDestinations
chosen
Indicates a relationship where something links or provides a route between multiple tourist destinations.
-
C.
hasCityAttractionConnection
Indicates a relationship where a city is linked to one of its attractions, such as a landmark, museum, or point of interest.
-
D.
attractionType
Indicates the specific kind or category of attraction that characterizes the relationship between entities.
-
E.
attractionBasedOn
Indicates a relationship where one entity is drawn to or interested in another specifically because of certain attributes, qualities, or characteristics that the latter possesses.
- 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_69e2fac350d08190b3affde1b451a8c5 |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f464b4c9b0819085daa00c7c3b8b76 |
completed | May 1, 2026, 8:30 a.m. |
| PD | Predicate disambiguation | batch_69f45cf017a88190b4985b11159c907d |
completed | May 1, 2026, 7:57 a.m. |
Created at: April 18, 2026, 5:22 a.m.