Triple
T19621259
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mount Roskill |
E471012
|
entity |
| Predicate | nearbySuburb |
P41355
|
FINISHED |
| Object | Three Kings |
—
|
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: Three Kings | Statement: [Mount Roskill, nearbySuburb, Three Kings]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Three Kings Context triple: [Mount Roskill, nearbySuburb, Three Kings]
-
A.
Three Kings
chosen
Three Kings is a residential suburb in Auckland, New Zealand, named after the nearby volcanic cones known as the Three Kings.
-
B.
Three Kings
Three Kings is a 1999 satirical war film set during the aftermath of the Gulf War, known for blending dark comedy with action and political commentary.
-
C.
Los Reyes
Los Reyes was one of the ships in the late 16th-century Spanish Pacific exploration fleet led by navigator Álvaro de Mendaña de Neira.
-
D.
Los Reyes
Los Reyes is a Mexico City Metro station serving the eastern area of the metropolitan zone on Line A.
-
E.
Table of the Three Kings
Table of the Three Kings is a mountain peak in the Pyrenees where the borders of Spain, France, and historically Navarre meet.
- 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_69d8e510fa248190b7afb274a1d4cf73 |
completed | April 10, 2026, 11:54 a.m. |
| NER | Named-entity recognition | batch_69e640e668408190bc1e12a336b0687b |
completed | April 20, 2026, 3:06 p.m. |
Created at: April 10, 2026, 1:43 p.m.