Triple
T9089805
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Instacart |
E217850
|
entity |
| Predicate | hasFounder |
P104
|
FINISHED |
| Object | Max Mullen |
E217850
|
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: Max Mullen | Statement: [Instacart, hasFounder, Max Mullen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Max Mullen Context triple: [Instacart, hasFounder, Max Mullen]
-
A.
Max Mullen
chosen
Max Mullen is an American entrepreneur best known as a co-founder of the grocery delivery company Instacart.
-
B.
Frank Mullen
Frank Mullen is an American death metal vocalist best known as the longtime frontman of the band Suffocation.
-
C.
John J. Haden
John J. Haden was an early 20th-century Florida horticulturist best known for developing the influential Haden mango cultivar that helped launch Florida’s commercial mango industry.
-
D.
Tony Mullen
Tony Mullen is a computer graphics and animation expert best known for his books and tutorials on Blender and 3D animation.
-
E.
Paul Satterfield
Paul Satterfield is a film professional known for his work as a sequence director on classic animated features such as Disney’s 1942 film "Bambi."
- 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_69ca83d8ab5881909d8fddae363b32b1 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc965971f88190acffbf204c11832b |
completed | April 1, 2026, 3:51 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d0774f0d7c8190b071e5b161622355 |
completed | April 4, 2026, 2:28 a.m. |
Created at: March 30, 2026, 7:14 p.m.