Triple
T29867398
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | gbXML |
E758493
|
entity |
| Predicate | typicalSourceSoftware |
P204016
|
FINISHED |
| Object | BIM authoring applications |
—
|
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: BIM authoring applications | Statement: [gbXML, typicalSourceSoftware, BIM authoring applications]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalSourceSoftware Context triple: [gbXML, typicalSourceSoftware, BIM authoring applications]
-
A.
typicalProgrammingSource
Indicates that one entity is a common or standard source from which the other entity obtains programming content or code.
-
B.
targetedSoftware
Indicates that a particular piece of software is the specific focus or target of an action, operation, or effect.
-
C.
mainSourceType
Indicates the primary category or kind of source from which something originates or is derived.
-
D.
softwareFamily
Indicates that one software product belongs to, or is categorized under, a broader family or line of related software.
-
E.
softwareFor
Indicates that one entity is designed, intended, or used to operate on, support, or be compatible with another entity as software.
- 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_69f2245b4dec8190b85f664d918a00a5 |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_6a030d3db2748190b32fcf7b21bd0d0a |
completed | May 12, 2026, 11:21 a.m. |
| PD | Predicate disambiguation | batch_6a030ca6bf388190b2f6931376323da3 |
completed | May 12, 2026, 11:19 a.m. |
| PDg | Predicate description generation | batch_6a030d3d14b48190a1858d37988e7fd6 |
completed | May 12, 2026, 11:21 a.m. |
Created at: April 29, 2026, 5:52 p.m.