Triple
T10344107
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Duke University West Campus |
E243698
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Abele Quad |
E696898
|
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: Abele Quad | Statement: [Duke University West Campus, contains, Abele Quad]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Abele Quad Context triple: [Duke University West Campus, contains, Abele Quad]
-
A.
Abele
chosen
Abele is a surname most notably associated with Julian Abele, a pioneering African American architect who contributed to the design of many prominent buildings in the early 20th century.
-
B.
Quarndon
Quarndon is a small village and civil parish in Derbyshire, England, situated just north of the city of Derby.
-
C.
Passalaqua
Passalaqua is the original family surname of renowned jazz guitarist Joe Pass, reflecting his Italian heritage.
-
D.
Odenberg
Odenberg is a Swedish surname most notably associated with politician Mikael Odenberg.
-
E.
Tetra Mound
Tetra Mound is a geometric, pyramid-like sculptural hill in Sapporo’s Moerenuma Park, designed as part of the park’s expansive landscape art.
- 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_69d381b22b8c8190aaed476be5f872a9 |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4e9228cd88190bcd94b85537233c1 |
completed | April 7, 2026, 11:23 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d75077dfbc81908de29aac1a3bb19f |
completed | April 9, 2026, 7:08 a.m. |
Created at: April 6, 2026, 11:55 a.m.