Triple
T15835316
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Austan Goolsbee |
E383969
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Austan |
E399616
|
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: Austan | Statement: [Austan Goolsbee, givenName, Austan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Austan Context triple: [Austan Goolsbee, givenName, Austan]
-
A.
Oloosson
Oloosson is an ancient town of Thessaly in Greece, known from classical sources and later identified with the modern area of Elassona.
-
B.
Nelsan
Nelsan is the given name of Nelsan Ellis, an American actor best known for his role as Lafayette Reynolds on the television series "True Blood."
-
C.
Auston
chosen
Auston is the given name of Auston Matthews, a prominent American professional ice hockey player in the NHL.
-
D.
Tolan
Tolan is a surname most notably associated with American television producer, writer, and director Peter Tolan.
-
E.
Boland
Boland is a rugby union region in South Africa whose teams and players are partly represented at the professional level by the Stormers franchise.
- 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_69d86da34c888190976e06c4019d415a |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e11e673e08819080c3f55a225607c7 |
completed | April 16, 2026, 5:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffa137be2c81909c8f04b5cc1a5b21 |
completed | May 9, 2026, 9:03 p.m. |
Created at: April 10, 2026, 4:49 a.m.