Triple
T36859618
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Whitworth standard screw thread |
E910896
|
entity |
| Predicate | threadDepth |
P188151
|
FINISHED |
| Object | 0.6403 × pitch |
—
|
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: 0.6403 × pitch | Statement: [Whitworth standard screw thread, threadDepth, 0.6403 × pitch]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: threadDepth Context triple: [Whitworth standard screw thread, threadDepth, 0.6403 × pitch]
-
A.
testDepth
Indicates that an entity is evaluated or measured based on how deep or thorough it is, often in terms of levels, layers, or extent below a surface or baseline.
-
B.
threadCount
Indicates the number of concurrent threads associated with an entity, such as a process, task, or execution context.
-
C.
searchDepth
Indicates the extent or level to which a search process explores through layers, steps, or hierarchy within a structure or space.
-
D.
hierarchyDepth
Indicates the level or distance of an entity from the top (root) within a hierarchical structure.
-
E.
poolDepth
Indicates the depth measurement of a pool at a specified location or overall.
- 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_69f76e8033d48190a59274f86f13be48 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fba2877b248190a974eb092243c0c4 |
completed | May 6, 2026, 8:20 p.m. |
| PD | Predicate disambiguation | batch_69fb8d06a1b48190a937aa410d159dfa |
completed | May 6, 2026, 6:48 p.m. |
| PDg | Predicate description generation | batch_69fba28684208190921694f23e350c3b |
completed | May 6, 2026, 8:20 p.m. |
Created at: May 3, 2026, 4:13 p.m.