Triple
T4143115
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Reed College |
E89318
|
entity |
| Predicate | hasBenefactor |
P10151
|
FINISHED |
| Object | Amanda Reed |
E89318
|
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: Amanda Reed | Statement: [Reed College, hasBenefactor, Amanda Reed]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Amanda Reed Context triple: [Reed College, hasBenefactor, Amanda Reed]
-
A.
Amanda Reed
chosen
Amanda Reed was the benefactor whose bequest and vision led to the establishment of Reed College in Portland, Oregon.
-
B.
Lana Lang
Lana Lang is a longtime supporting character in the Superman franchise, best known as Clark Kent’s childhood friend and early love interest from Smallville.
-
C.
Gwen Cooper
Gwen Cooper is a compassionate yet tough Welsh police officer who becomes a key member of the secret alien-hunting team in the British sci-fi series Torchwood.
-
D.
Sharon Maguire
Sharon Maguire is a British film director best known for helming the hit romantic comedy "Bridget Jones’s Diary."
-
E.
Kate Bishop
Kate Bishop is a young, skilled archer and protégé of Clint Barton in the Marvel universe who takes up the Hawkeye mantle.
- 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_69aed95785788190ae75bcf0cd1cafdf |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69af024cc7e88190b23b39d6f5f2a2e0 |
completed | March 9, 2026, 5:24 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b57f2e787881908a9721877b0fd4ae |
completed | March 14, 2026, 3:30 p.m. |
Created at: March 9, 2026, 3:43 p.m.