Triple
T8003530
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jack Altman |
E186308
|
entity |
| Predicate | hasFounded |
P6274
|
FINISHED |
| Object | Lattice |
E704264
|
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: Lattice | Statement: [Jack Altman, hasFounded, Lattice]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lattice Context triple: [Jack Altman, hasFounded, Lattice]
-
A.
Lattice
chosen
Lattice is a software company that provides people management and performance review tools to help organizations develop and engage their employees.
-
B.
Lattice Sentry
Lattice Sentry is a hardware security platform from Lattice Semiconductor designed to provide real-time, FPGA-based root-of-trust and system protection for embedded applications.
-
C.
Lattice Automate
Lattice Automate is an edge AI and industrial automation solution platform from Lattice Semiconductor designed to accelerate development of smart, low-power, and real-time control systems.
-
D.
Leech lattice
The Leech lattice is a highly symmetric 24-dimensional lattice in Euclidean space, notable for its dense sphere packing and deep connections to sporadic simple groups and modular forms.
-
E.
Lattice sensAI
Lattice sensAI is Lattice Semiconductor’s low-power, FPGA-based edge AI platform designed to accelerate machine learning inference in resource-constrained applications.
- 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_69ca82aaaf24819084b94d18f699ba53 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3cf443e48190ac9e83343ff4019e |
completed | March 31, 2026, 3:18 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cc5697ac9081909fe7ca06d0c3ef38 |
completed | March 31, 2026, 11:19 p.m. |
Created at: March 30, 2026, 5:18 p.m.