Triple
T93
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Differential analyzer |
E1
|
entity |
| Predicate | requires |
P100
|
FINISHED |
| Object | manual configuration of shafts and gears |
—
|
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: manual configuration of shafts and gears | Statement: [Differential analyzer, requires, manual configuration of shafts and gears]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: requires Context triple: [Differential analyzer, requires, manual configuration of shafts and gears]
-
A.
influenced
Indicates that one entity has affected, shaped, or altered another entity’s state, behavior, or characteristics.
-
B.
fieldOfWork
Indicates the professional or academic domain in which an entity is primarily engaged or specializes.
-
C.
notableFor
Indicates that an entity is especially recognized or distinguished for a particular quality, achievement, characteristic, or role.
-
D.
memberOf
Indicates that an entity belongs to, is part of, or is a constituent of a larger group, organization, or collection.
-
E.
employer
Indicates a relationship where one entity hires, pays, and oversees the work of another entity.
- 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_69a222a954e48190b48f126a67485661 |
completed | Feb. 27, 2026, 11:03 p.m. |
| NER | Named-entity recognition | batch_69a2266edf048190828e8f53cb7f6ba6 |
completed | Feb. 27, 2026, 11:19 p.m. |
| PD | Predicate disambiguation | batch_69a222f9916081908db2eedc81d85301 |
completed | Feb. 27, 2026, 11:04 p.m. |
| PDg | Predicate description generation | batch_69a2266e0fb4819081d1775e498ed96a |
completed | Feb. 27, 2026, 11:19 p.m. |
Created at: Feb. 27, 2026, 11:04 p.m.