Triple
T18105383
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Makahiki festival |
E433334
|
entity |
| Predicate | hasMainDeity |
P7648
|
FINISHED |
| Object | Lono |
—
|
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: Lono | Statement: [Makahiki festival, hasMainDeity, Lono]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lono Context triple: [Makahiki festival, hasMainDeity, Lono]
-
A.
Lono
chosen
Lono is a principal Hawaiian god associated with agriculture, fertility, rainfall, and the Makahiki harvest festival.
-
B.
Lono
Lono is a violent, psychopathic enforcer and one of the central, most feared members of the Minutemen in the crime comic series "100 Bullets."
-
C.
Hāla
Hāla was an ancient Indian king of the Satavahana dynasty traditionally credited with composing the Prakrit love-poem anthology Gaha Sattasai.
-
D.
Kaiolohia
Kaiolohia, also known as Shipwreck Beach, is a remote, rugged stretch of coastline on the Hawaiian island of Lānaʻi noted for its offshore shipwrecks and scenic views.
-
E.
ʻOhonua
ʻOhonua is the main town and administrative center of the Tongan island of ʻEua in the South Pacific.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b90916008190a1f110bd7ced5473 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4ddb9981c8190b33697fbcaa901b3 |
completed | April 19, 2026, 1:50 p.m. |
Created at: April 10, 2026, 10:28 a.m.