Triple
T12302835
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Phantoscope |
E293273
|
entity |
| Predicate | hasAlternativeName |
P39
|
FINISHED |
| Object | Jenkins–Armat Phantoscope |
E293273
|
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: Jenkins–Armat Phantoscope | Statement: [Phantoscope, hasAlternativeName, Jenkins–Armat Phantoscope]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jenkins–Armat Phantoscope Context triple: [Phantoscope, hasAlternativeName, Jenkins–Armat Phantoscope]
-
A.
Phantoscope
chosen
The Phantoscope was an early motion picture projector whose design formed the basis for later commercial projectors like the Vitascope.
-
B.
Panoptix
Panoptix is a Johnson Controls software platform that provides cloud-based building management and energy optimization solutions.
-
C.
Jennet Device
Jennet Device was a young key witness whose testimony was crucial in securing convictions during the infamous 1612 Pendle witch trials in Lancashire, England.
-
D.
The Ellie
The Ellie is a renowned opera house and performing arts venue in Denver, Colorado, known for hosting opera, ballet, and other major cultural events.
-
E.
Metreon
Metreon is a large entertainment and retail complex in downtown San Francisco featuring shops, restaurants, a movie theater, and event spaces.
- 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_69d6ab6a2b50819082f6aedd32ed608a |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d93edca2648190987eef19599e340c |
completed | April 10, 2026, 6:18 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f61e7d757881908ac6af2b70a6dafe |
completed | May 2, 2026, 3:55 p.m. |
Created at: April 8, 2026, 9:53 p.m.