Triple
T2952123
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Precision Castparts |
E79842
|
entity |
| Predicate | manufacturingProcess |
P35199
|
FINISHED |
| Object | investment casting |
—
|
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: investment casting | Statement: [Precision Castparts, manufacturingProcess, investment casting]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: manufacturingProcess Context triple: [Precision Castparts, manufacturingProcess, investment casting]
-
A.
hasProductionMethod
chosen
Indicates that one entity is produced, created, or manufactured using the method, process, or technique specified by another entity.
-
B.
designProcess
Indicates the sequence of actions, decisions, and iterations involved in creating, developing, or refining a design.
-
C.
partOfProcess
Indicates that one event, step, or action occurs as a component or stage within a larger overall process.
-
D.
typicalProductionType
Indicates the usual or characteristic type of production activity associated with an entity.
-
E.
produces
Indicates that one entity creates, generates, or yields another entity as a result or output.
- 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_69ad8b1276588190a374a0b12e0f7bdf |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad98fcea5c8190b7d80de942bcb4f7 |
completed | March 8, 2026, 3:42 p.m. |
| PD | Predicate disambiguation | batch_69ad960a70ac8190816b5ae3e8631031 |
completed | March 8, 2026, 3:30 p.m. |
Created at: March 8, 2026, 2:57 p.m.