Triple
T9465974
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Late Night |
E228270
|
entity |
| Predicate | hostTenureDavidLettermanStart |
P20544
|
FINISHED |
| Object | 1982 |
—
|
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: 1982 | Statement: [Late Night, hostTenureDavidLettermanStart, 1982]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hostTenureDavidLettermanStart Context triple: [Late Night, hostTenureDavidLettermanStart, 1982]
-
A.
inauguralSeasonTenant
Indicates that the subject entity served as a tenant (e.g., occupant or user of a venue or facility) during the venue’s inaugural season.
-
B.
tenantsStart
chosen
Indicates that a tenancy relationship begins or is initiated at a specific time or event.
-
C.
hostFranchise
Indicates that one entity serves as the host organization or location for a particular franchise associated with another entity.
-
D.
formerCityHost
Indicates that a city previously served as a host for a particular event, role, or function but no longer does so.
-
E.
mainTenant
Indicates that the subject is the primary tenant responsible for a property or rental agreement, as opposed to a subtenant or secondary occupant.
- 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_69ca846fee388190a6ec273fd644b88b |
completed | March 30, 2026, 2:10 p.m. |
| NER | Named-entity recognition | batch_69cd7fdc08f08190ad17de08d2c2eca2 |
completed | April 1, 2026, 8:28 p.m. |
| PD | Predicate disambiguation | batch_69cca55caaa8819089c5138e014892d3 |
completed | April 1, 2026, 4:55 a.m. |
Created at: March 30, 2026, 7:53 p.m.