Triple
T26890640
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cornelius Vander Starr |
E677160
|
entity |
| Predicate | startedInsuranceOperationsIn |
P123998
|
FINISHED |
| Object | Shanghai |
—
|
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: Shanghai | Statement: [Cornelius Vander Starr, startedInsuranceOperationsIn, Shanghai]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: startedInsuranceOperationsIn Context triple: [Cornelius Vander Starr, startedInsuranceOperationsIn, Shanghai]
-
A.
trialOperationsBegan
Indicates that the operational phase of a trial has started.
-
B.
initiallyOperated
Indicates that an entity first began functioning, being used, or carrying out its intended operation at a specified initial time or under initial conditions.
-
C.
startedNear
Indicates that one event or action began close in time or space to another event or action.
-
D.
initiatedIn
chosen
Indicates that an action, process, or event was started or first brought into effect within a specified context, such as a place, time, or situation.
-
E.
startedBusinessWith
Indicates that two or more entities jointly initiated or founded a business together.
- 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_69eee9bc0c90819085608c8bdc513a57 |
completed | April 27, 2026, 4:44 a.m. |
| NER | Named-entity recognition | batch_69f79f48acec8190a9d5964581a94f6c |
completed | May 3, 2026, 7:17 p.m. |
| PD | Predicate disambiguation | batch_69f79e4888248190be2f63cdfb5cd7b7 |
completed | May 3, 2026, 7:13 p.m. |
Created at: April 27, 2026, 5:44 a.m.