Triple
T15062393
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Max Hodak |
E379661
|
entity |
| Predicate | hasTwitterHandle |
P2943
|
FINISHED |
| Object | @max_hodak |
E379661
|
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_hodak | Statement: [Max Hodak, hasTwitterHandle, @max_hodak]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: @max_hodak Context triple: [Max Hodak, hasTwitterHandle, @max_hodak]
-
A.
@max_hodak
chosen
@max_hodak is the Twitter handle of Max Hodak, a technology entrepreneur best known as the co-founder and former president of Neuralink and founder of biotech startup Science Corp.
-
B.
Max-D
Max-D is a famous Monster Jam freestyle and racing monster truck known for its spiked body, aggressive design, and high-flying stunts.
-
C.
Maximowicz
Maximowicz was a 19th-century Russian botanist and explorer known for his extensive taxonomic work on East Asian flora.
-
D.
MAX
MAX is a family of low-cost, high-density CPLD (Complex Programmable Logic Device) products developed by Altera for implementing customizable digital logic functions.
-
E.
MAX
MAX is the Portland metropolitan area’s light rail transit system, operated by TriMet and serving multiple lines across the region.
- 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_69d85cd7683881908d405c1b5d7b4f7f |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69dedee6a55c8190b40c4672fb46b79b |
completed | April 15, 2026, 12:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fea5c612d481909575b76f7aa96c50 |
completed | May 9, 2026, 3:11 a.m. |
Created at: April 10, 2026, 3:02 a.m.