Triple
T25620768
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ADEA |
E642289
|
entity |
| Predicate | minimumEmployerSize |
P74492
|
FINISHED |
| Object | 20 or more employees |
—
|
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: 20 or more employees | Statement: [ADEA, minimumEmployerSize, 20 or more employees]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: minimumEmployerSize Context triple: [ADEA, minimumEmployerSize, 20 or more employees]
-
A.
appliesToEmployerSize
chosen
Indicates that something (such as a rule, policy, or condition) is applicable only to employers of a specified size or within a defined employer size range.
-
B.
minimumNumberOfMembers
Indicates the smallest allowable or required number of members that must be present or involved in a given context or group.
-
C.
minimumSize
Indicates that there is a lower bound or smallest allowable value for the size of something in the relationship.
-
D.
minimumEmployeeThresholdPerCountry
Indicates the minimum number of employees that must be present or maintained in each country.
-
E.
typicalCompanySize
Indicates the usual or most common number of employees associated with a company.
- 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_69e77e7a96748190b10f2699041e4e43 |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f5fa204d1c8190b441d4efd8d80940 |
completed | May 2, 2026, 1:20 p.m. |
| PD | Predicate disambiguation | batch_69f4a0f7c6008190ae8cee3e71e19b94 |
completed | May 1, 2026, 12:47 p.m. |
Created at: April 21, 2026, 5:04 p.m.