Triple
T36235830
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Peter the Great worked incognito in Dutch shipyards |
E891375
|
entity |
| Predicate | hasEmployerDuringEvent |
P125493
|
FINISHED |
| Object | Dutch East India Company |
—
|
NE NERFINISHED |
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: Dutch East India Company | Statement: [Peter the Great worked incognito in Dutch shipyards, hasEmployerDuringEvent, Dutch East India Company]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasEmployerDuringEvent Context triple: [Peter the Great worked incognito in Dutch shipyards, hasEmployerDuringEvent, Dutch East India Company]
-
A.
employedAtTime
chosen
Indicates that an employment relationship holds during a specified time or time interval.
-
B.
workedAtEvent
Indicates that an entity performed work or provided services at a specific event.
-
C.
hasWorkedFor
Indicates that an entity has been employed by or has provided work or services to another entity.
-
D.
employerDuringUse
Indicates that one entity is the employer of another entity for the duration of a specified use, activity, or period.
-
E.
hasWorkedIn
Indicates that a person has been employed or has performed work within a particular organization, location, or domain for some period of time.
- 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_69f76e4387048190a1b27bcbf4ec7423 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7be9d07ac8190adf796cbef60daf6 |
completed | May 3, 2026, 9:31 p.m. |
| PD | Predicate disambiguation | batch_69f7bcccd7988190aa5c931ff347d33c |
completed | May 3, 2026, 9:23 p.m. |
Created at: May 3, 2026, 4:09 p.m.