Triple
T16268804
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Walter Sisulu University |
E394942
|
entity |
| Predicate | hasCampusIn |
P4623
|
FINISHED |
| Object | Butterworth |
E877314
|
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: Butterworth | Statement: [Walter Sisulu University, hasCampusIn, Butterworth]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Butterworth Context triple: [Walter Sisulu University, hasCampusIn, Butterworth]
-
A.
Butterworth
Butterworth is a major town in Penang, Malaysia, serving as an important transport and industrial hub with key road, rail, and ferry links.
-
B.
Butterworth
Butterworth is an English surname borne by various notable individuals, including playwright and screenwriter Jez Butterworth.
-
C.
Butterworth
chosen
Butterworth is a historic town in South Africa’s Eastern Cape province, known as one of the oldest settlements in the former Transkei region and a regional commercial center.
-
D.
Bode
The Bode is a river in central Germany that flows through the Harz Mountains and Saxony-Anhalt before joining the Saale.
-
E.
Bode
Bode is a surname most notably associated with Hendrik Wade Bode, an influential American engineer and pioneer in control theory and communication systems.
- 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_69d87f221d8081909b0b2063e7528ba2 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e245ca5c708190a1e98ab37740c032 |
completed | April 17, 2026, 2:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0017bb1d64819080f007656307f58b |
completed | May 10, 2026, 5:29 a.m. |
Created at: April 10, 2026, 5:05 a.m.