Triple
T18198825
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | WIRCam |
E435728
|
entity |
| Predicate | siteLocation |
P3231
|
FINISHED |
| Object | Mauna Kea, Hawaii |
—
|
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: Mauna Kea, Hawaii | Statement: [WIRCam, siteLocation, Mauna Kea, Hawaii]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mauna Kea, Hawaii Context triple: [WIRCam, siteLocation, Mauna Kea, Hawaii]
-
A.
Mauna Kea
chosen
Mauna Kea is a dormant volcano on Hawaii’s Big Island renowned both as the state’s tallest mountain and as one of the world’s premier sites for astronomical observatories.
-
B.
Mauna Loa
Mauna Loa is one of the world’s largest and most active shield volcanoes, dominating much of Hawaii’s Big Island.
-
C.
Maunu
Maunu is a residential suburb located on the southwestern outskirts of Whangārei in New Zealand’s Northland Region.
-
D.
Mount Kaʻala
Mount Kaʻala is the tallest mountain on the Hawaiian island of Oʻahu, known for its flat summit plateau and unique native ecosystems.
-
E.
Haleakalā volcano
Haleakalā volcano is a massive shield volcano on the island of Maui in Hawaii, renowned for its vast summit crater, dramatic volcanic landscapes, and spectacular sunrise views.
- 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_69d8b90dba6481908e119eb9aa4ca0cb |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4e0d545f4819090285d1446bd3c27 |
completed | April 19, 2026, 2:04 p.m. |
Created at: April 10, 2026, 10:31 a.m.