Triple
T26071299
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Île Seguin |
E657551
|
entity |
| Predicate | industrialPeakEmployment |
P23435
|
FINISHED |
| Object | tens of thousands of workers |
—
|
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: tens of thousands of workers | Statement: [Île Seguin, industrialPeakEmployment, tens of thousands of workers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: industrialPeakEmployment Context triple: [Île Seguin, industrialPeakEmployment, tens of thousands of workers]
-
A.
historicalPeakIndustrialPeriod
Indicates the time period during which an entity reached its highest level of industrial activity or development.
-
B.
unemploymentPeak
Indicates that the level of unemployment has reached its highest point within a specified time period or context.
-
C.
numberOfEmployeesAtPeak
Indicates the highest recorded count of employees that an entity had at any point in time.
-
D.
hasIndustrialEmployer
Indicates that an entity is employed by, or has an employment relationship with, an industrial organization or company.
-
E.
peakEmployment
chosen
Indicates that an entity has reached its highest level of employment or workforce size during a specified period.
- 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_69ee5bbe539081909efc7f9dd7c1b53c |
completed | April 26, 2026, 6:38 p.m. |
| NER | Named-entity recognition | batch_69f62d89b89c8190afb372a8172111e7 |
completed | May 2, 2026, 4:59 p.m. |
| PD | Predicate disambiguation | batch_69f62c1379f08190836c3e02b0c892df |
completed | May 2, 2026, 4:53 p.m. |
Created at: April 26, 2026, 7:29 p.m.