Triple
T23000953
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Scarborough Country |
E572629
|
entity |
| Predicate | hostedByFormer |
P46400
|
FINISHED |
| Object | United States congressman |
—
|
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: United States congressman | Statement: [Scarborough Country, hostedByFormer, United States congressman]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hostedByFormer Context triple: [Scarborough Country, hostedByFormer, United States congressman]
-
A.
hasFormerHost
chosen
Indicates that an entity previously served as the host of another entity but no longer holds that hosting role.
-
B.
hostedBySince
Indicates that one entity has been continuously hosted or accommodated by another entity starting from a specified point in time.
-
C.
formerCityHost
Indicates that a city previously served as a host for a particular event, role, or function but no longer does so.
-
D.
hasBeenHostedIn
Indicates that an event, show, or activity took place or was conducted at a particular location or venue in the past.
-
E.
formerCoHostOf
Indicates that one entity previously served as a co-host together with another entity, but no longer holds that co-hosting role.
- 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_69e245b6a3ac81908087599eefe3e365 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18352bcf48190bd474eff69b3465b |
completed | April 29, 2026, 4:04 a.m. |
| PD | Predicate disambiguation | batch_69ef3b9cd5488190bcd23183179f48cd |
completed | April 27, 2026, 10:34 a.m. |
Created at: April 17, 2026, 3:50 p.m.