Triple
T10120968
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Adrian Hanauer |
E223286
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Adrian Hanauer |
E223286
|
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: Adrian Hanauer | Statement: [Adrian Hanauer, name, Adrian Hanauer]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Adrian Hanauer Context triple: [Adrian Hanauer, name, Adrian Hanauer]
-
A.
Adrian Hanauer
chosen
Adrian Hanauer is an American businessman best known as the majority owner and longtime executive leader of Major League Soccer’s Seattle Sounders FC.
-
B.
Joe Hahn
Joe Hahn is an American musician and DJ best known as the turntablist and sampler for the rock band Linkin Park.
-
C.
Robert Hohman
Robert Hohman is an American entrepreneur best known as the co-founder and former CEO of Glassdoor, a popular platform for anonymous employee reviews and salary information.
-
D.
Ed Heinemann
Ed Heinemann was a renowned American aeronautical engineer best known for designing innovative and influential military aircraft for Douglas Aircraft Company during the mid-20th century.
-
E.
Doug J. Hannah
Doug J. Hannah is a film editor best known for his work on the science fiction thriller "The Cloverfield Paradox."
- 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_69ca8422047c81909d66b717b8b18cf3 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cdd266b18c8190b35fe637c912e756 |
completed | April 2, 2026, 2:20 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d3174bc46081909d78cdb524625ec3 |
completed | April 6, 2026, 2:15 a.m. |
Created at: March 30, 2026, 9:04 p.m.