Triple
T4351149
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lono |
E98028
|
entity |
| Predicate | festival |
P3113
|
FINISHED |
| Object | Makahiki |
E433334
|
NE 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: Makahiki | Statement: [Lono, festival, Makahiki]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Makahiki Context triple: [Lono, festival, Makahiki]
-
A.
Makahiki festival
chosen
The Makahiki festival is an ancient Hawaiian New Year season marked by religious ceremonies, feasting, games, and a kapu (prohibition) on war in honor of the god Lono.
-
B.
Nuʻuuli
Nuʻuuli is a village and commercial center on the island of Tutuila in American Samoa.
-
C.
Moku Iki
Moku Iki is one of the small offshore Mokulua islets near Lanikai on Oʻahu, known for its scenic volcanic landscape and seabird sanctuary status.
-
D.
Waigali
Waigali is a Nuristani language spoken by the Waigal Valley communities in eastern Afghanistan, known for preserving archaic features distinct from surrounding Indo-Aryan and Iranian languages.
-
E.
Tanimaiaki
Tanimaiaki is a settlement on the atoll of Abemama in the island nation of Kiribati in the central Pacific Ocean.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69b3454965f881908c41190bb22f0e4b |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b351a99788819080b13a20124e49a0 |
completed | March 12, 2026, 11:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5f5d00e20819095114787f95e3858 |
completed | March 14, 2026, 11:57 p.m. |
Created at: March 12, 2026, 11:15 p.m.