Triple
T30774059
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fujifilm X-H2 |
E783609
|
entity |
| Predicate | ibisCompensation |
P170114
|
FINISHED |
| Object | up to 7 stops |
—
|
LITERAL 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: up to 7 stops | Statement: [Fujifilm X-H2, ibisCompensation, up to 7 stops]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ibisCompensation Context triple: [Fujifilm X-H2, ibisCompensation, up to 7 stops]
-
A.
IBISCompensation
Indicates a relationship where an entity provides or receives compensation specifically associated with the IBIS (Integrated Business Information System) context.
-
B.
compensationModel
Indicates the type or structure of payment or rewards provided in exchange for work, services, or performance.
-
C.
compensationIncludes
Indicates that a specified form of payment or benefit is part of the overall compensation provided in a given context.
-
D.
compensationCategory
Indicates the type or classification of compensation associated with an entity, such as how or in what form payment or remuneration is provided.
-
E.
compensationTrigger
Indicates the event or condition that initiates or authorizes a compensation or payment to be made.
- F. None of above. chosen
Provenance (4 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_69f224b1519081908b9db003fd2073e0 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f68fe016688190b2fe1f6931ee1e48 |
completed | May 2, 2026, 11:59 p.m. |
| PD | Predicate disambiguation | batch_69f686140aa08190a35f62572b2db9b6 |
completed | May 2, 2026, 11:17 p.m. |
| PDg | Predicate description generation | batch_69f68848ad348190a2fb6e841dcfdb7d |
completed | May 2, 2026, 11:27 p.m. |
Created at: April 29, 2026, 8:40 p.m.