Triple
T15839608
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MAXI |
E384067
|
entity |
| Predicate | acronym |
P43
|
FINISHED |
| Object | MAXI |
E384067
|
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: MAXI | Statement: [MAXI, acronym, MAXI]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: MAXI Context triple: [MAXI, acronym, MAXI]
-
A.
MAXI
chosen
MAXI is an X-ray astronomy mission that continuously monitors the sky for high-energy phenomena such as black hole outbursts, neutron star activity, and other transient cosmic events.
-
B.
Maxi
Maxi is a retail store or supermarket chain where the product "No Name" is sold.
-
C.
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.
-
D.
MAX
MAX is the Portland metropolitan area’s light rail transit system, operated by TriMet and serving multiple lines across the region.
-
E.
MAX
MAX is a Marvel Comics imprint created for mature readers, featuring darker, more explicit stories often starring grittier versions of established characters.
- 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_69e142e69360819091ea0556bd66d785 |
completed | April 16, 2026, 8:13 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffa13c931481908ed9fd10fddd867c |
completed | May 9, 2026, 9:03 p.m. |
Created at: April 10, 2026, 4:49 a.m.