Triple
T9747446
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | University of Sunderland |
E236349
|
entity |
| Predicate | memberOf |
P10
|
FINISHED |
| Object | MillionPlus |
E119407
|
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: MillionPlus | Statement: [University of Sunderland, memberOf, MillionPlus]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: MillionPlus Context triple: [University of Sunderland, memberOf, MillionPlus]
-
A.
MillionPlus
chosen
MillionPlus is a UK-based university think tank and advocacy group representing modern universities and championing their role in higher education and society.
-
B.
MillionPlus group
The MillionPlus group is a UK-based association representing modern universities that focus on widening participation, applied research, and regional economic development.
-
C.
Music for Millions
Music for Millions is a 1944 American musical comedy-drama film best known for its heartwarming World War II-era story and ensemble cast, including Phillip Terry.
-
D.
Untold Millions
"Untold Millions" is a novel by American author Laura Z. Hobson, best known for exploring social issues and human relationships.
-
E.
Milles
Milles is a surname and variant of "Mills" that appears in English-speaking contexts.
- 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_69ca84d3e24481908a476e2231123cf9 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cd9f677830819096d388b9c798ecd5 |
completed | April 1, 2026, 10:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1b00d76488190af68cba694dc329c |
completed | April 5, 2026, 12:42 a.m. |
Created at: March 30, 2026, 8:23 p.m.