Triple
T1891996
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Handycam |
E41893
|
entity |
| Predicate | marketedAs |
P1395
|
FINISHED |
| Object | Sony Handycam |
E41893
|
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: Sony Handycam | Statement: [Handycam, marketedAs, Sony Handycam]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sony Handycam Context triple: [Handycam, marketedAs, Sony Handycam]
-
A.
Handycam
chosen
Handycam is Sony’s well-known line of compact consumer camcorders designed for easy handheld video recording.
-
B.
Cyber-shot
Cyber-shot is Sony's line of compact digital still cameras known for their portability, advanced imaging features, and consumer-friendly design.
-
C.
HDR200
HDR200 is a high-speed InfiniBand interconnect generation that delivers up to 200 Gbit/s bandwidth per port for data center and high-performance computing networks.
-
D.
Megacam
Megacam is a wide-field optical imaging camera used on large ground-based telescopes for deep, high-resolution astronomical surveys.
-
E.
Holga
Holga is a fictional character appearing in the post-apocalyptic virtual reality shooter game "After the Fall."
- 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_69a8864b6de0819098d089f6a1b910a7 |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69abb145f96c8190a71bb9e442892e68 |
completed | March 7, 2026, 5:01 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69addf68a8d48190a3360557def67692 |
completed | March 8, 2026, 8:43 p.m. |
Created at: March 4, 2026, 7:34 p.m.