Triple
T23843206
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vernooy family |
E591041
|
entity |
| Predicate | hasEarlyPresenceIn |
P97108
|
FINISHED |
| Object | Ulster County, New York |
—
|
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: Ulster County, New York | Statement: [Vernooy family, hasEarlyPresenceIn, Ulster County, New York]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasEarlyPresenceIn Context triple: [Vernooy family, hasEarlyPresenceIn, Ulster County, New York]
-
A.
earlyPresence
chosen
Indicates that one entity is present or arrives earlier than another reference point, event, or entity.
-
B.
hasEarlyRoleFor
Indicates that one entity holds or performs an initial or early-stage role in relation to another entity or process.
-
C.
hasHumanPresence
Indicates that humans are physically present in or occupying a given location, object, or context.
-
D.
hasLargePresenceIn
Indicates that an entity maintains a significant or dominant level of activity, influence, or representation within a specified location, domain, or context.
-
E.
meetsInPresenceOf
Indicates that two or more entities meet or interact while another specified entity is present as a witness, chaperone, or contextual participant.
- 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_69e25d1de32c8190a907afe9c3d6cd6d |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1c8898a0c8190b4d55852fc30260f |
completed | April 29, 2026, 8:59 a.m. |
| PD | Predicate disambiguation | batch_69f1614612b481908c45d99e588882f9 |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 8:09 p.m.