Triple
T9712829
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Butane |
E235060
|
entity |
| Predicate | primaryOutputFormat |
P50897
|
FINISHED |
| Object | Ignition configuration |
—
|
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: Ignition configuration | Statement: [Butane, primaryOutputFormat, Ignition configuration]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryOutputFormat Context triple: [Butane, primaryOutputFormat, Ignition configuration]
-
A.
primaryOutput
Indicates that the related entity is the main or principal result, product, or outcome produced by another entity or process.
-
B.
distributedFormat
chosen
Indicates that an entity is made available or disseminated in a particular format or medium.
-
C.
outputOf
Indicates that one entity is the result or product generated by the processing, operation, or behavior of another entity.
-
D.
standardOutput
Indicates that one entity produces data or results that are directed to another entity’s standard output stream.
-
E.
outputProperty
Indicates that a property or attribute is produced, exposed, or yielded as the output of a process, function, or system.
- F. None of above.
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_69ca84cd8fa0819090a5e243ceb37003 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cd9e0705f8819095852263009c28c5 |
completed | April 1, 2026, 10:36 p.m. |
| PD | Predicate disambiguation | batch_69cd03bfeca08190924fca43aaa9c10f |
completed | April 1, 2026, 11:38 a.m. |
Created at: March 30, 2026, 8:19 p.m.