Triple
T16334896
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marsden Wharf |
E396651
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Auckland |
E18491
|
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: Auckland | Statement: [Marsden Wharf, locatedIn, Auckland]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Auckland Context triple: [Marsden Wharf, locatedIn, Auckland]
-
A.
Auckland
chosen
Auckland is a major New Zealand metropolis known for its harbors, multicultural population, and role as the country’s primary economic and transport hub.
-
B.
Wellington
Wellington is a regional town in New South Wales, Australia, known for its agricultural surroundings and location near the junction of the Macquarie and Bell rivers.
-
C.
Wellington
Wellington is a market town in Shropshire, England, now part of the borough of Telford and Wrekin.
-
D.
Wellington
Wellington is a small village in Lorain County, Ohio, known for its historic downtown and rural Midwestern character.
-
E.
Wellington
Wellington is a small town in northern Colorado, United States, located just north of Fort Collins and known as a growing residential community along the Interstate 25 corridor.
- 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_69d87f26864c819088365ca381a003c2 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e2c4e29db88190936a07deb5b1c1e3 |
completed | April 17, 2026, 11:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0025f183d88190b269233ff6e65d75 |
completed | May 10, 2026, 6:30 a.m. |
Created at: April 10, 2026, 5:07 a.m.