Triple
T1552597
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | General Motors board of directors |
E33125
|
entity |
| Predicate | hasMinimumSize |
P31165
|
FINISHED |
| Object | more than 5 directors |
—
|
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: more than 5 directors | Statement: [General Motors board of directors, hasMinimumSize, more than 5 directors]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMinimumSize Context triple: [General Motors board of directors, hasMinimumSize, more than 5 directors]
-
A.
hasMinimumValue
Indicates that an entity possesses a value that is the lowest permissible or observed within a specified set, range, or context.
-
B.
hasMinimumLength
Indicates that the length of an entity (such as a sequence, string, or collection) is greater than or equal to a specified minimum value.
-
C.
headerMinimumSize
Indicates that there is a constraint specifying the smallest allowable size for a header.
-
D.
isMinimumWhen
Indicates that a value or state is at its smallest or least level precisely under certain specified conditions or circumstances.
-
E.
minimumWidth
Indicates that there is a specified smallest allowable or required width for something in the relationship.
- 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_69a885ee6db8819099502bc5ce8af881 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69aa574094048190a2d7fc3ac904d51e |
completed | March 6, 2026, 4:25 a.m. |
| PD | Predicate disambiguation | batch_69a907b426dc8190975c024a50955368 |
completed | March 5, 2026, 4:33 a.m. |
| PDg | Predicate description generation | batch_69aa573ee8e0819084abf59f1ddbd1da |
completed | March 6, 2026, 4:25 a.m. |
Created at: March 4, 2026, 7:26 p.m.