Triple
T7088424
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tony Hsieh |
E165132
|
entity |
| Predicate | coFounded |
P104
|
FINISHED |
| Object | LinkExchange |
E640000
|
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: LinkExchange | Statement: [Tony Hsieh, coFounded, LinkExchange]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: LinkExchange Context triple: [Tony Hsieh, coFounded, LinkExchange]
-
A.
LinkExchange
chosen
LinkExchange was an early online advertising network and banner exchange service that became one of the first major dot-com successes before being acquired by Microsoft in 1998.
-
B.
LinkPass
LinkPass is a type of transit fare product used within the same system as the CharlieTicket, providing riders with a pass-based option for public transportation access.
-
C.
Links Market
Links Market is a historic annual funfair held in Kirkcaldy, Scotland, known as one of Europe’s longest street fairs with a wide variety of rides, stalls, and attractions.
-
D.
ELink
ELink is an NCBI E-utilities tool that retrieves and navigates links between related records across NCBI databases.
-
E.
Getlink
Getlink is a French-based company that owns and operates the infrastructure of the Channel Tunnel rail link between the United Kingdom and continental Europe.
- 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_69c6887d98408190912b9580666b0c1d |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6e52d26f08190917e5e13b181bdae |
completed | March 27, 2026, 8:14 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c79c924ac88190a237d2e0ac505d51 |
completed | March 28, 2026, 9:17 a.m. |
Created at: March 27, 2026, 2:41 p.m.