Triple
T14592860
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Back Award |
E342486
|
entity |
| Predicate | hasRecipient |
P108
|
FINISHED |
| Object | Brian Berry |
E1109431
|
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: Brian Berry | Statement: [Back Award, hasRecipient, Brian Berry]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Brian Berry Context triple: [Back Award, hasRecipient, Brian Berry]
-
A.
Brian Berry
chosen
Brian Berry is a prominent British geographer known for his influential work in urban and regional analysis and contributions to quantitative geography.
-
B.
Dan Truman
Dan Truman is an American country musician best known as the keyboardist for the Grammy-winning band Diamond Rio.
-
C.
Dan Truman
Dan Truman is the NASA administrator in the 1998 disaster film "Armageddon," responsible for overseeing the mission to prevent an asteroid from destroying Earth.
-
D.
Mark Connally
Mark Connally is the son of former Texas First Lady Nellie Connally and prominent Texas politician John Connally.
-
E.
Ros Bailey
Ros Bailey is a fictional executive character in the "Fifty Shades" series who serves in a senior leadership role at Christian Grey’s company.
- 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_69d822ddc0f081909cd8163c7de298cd |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb43480d8819084a707e56da2c237 |
completed | April 14, 2026, 9:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fde169eb6481909d7fac6d984a2af1 |
completed | May 8, 2026, 1:13 p.m. |
Created at: April 10, 2026, 1:24 a.m.