Triple
T28675627
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ed McMahon’s "Heeere’s Johnny!" introduction of Johnny Carson |
E725853
|
entity |
| Predicate | firstRegularUseApprox |
P102639
|
FINISHED |
| Object | 1960s |
—
|
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: 1960s | Statement: [Ed McMahon’s "Heeere’s Johnny!" introduction of Johnny Carson, firstRegularUseApprox, 1960s]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstRegularUseApprox Context triple: [Ed McMahon’s "Heeere’s Johnny!" introduction of Johnny Carson, firstRegularUseApprox, 1960s]
-
A.
firstPerformanceApproximate
chosen
Indicates that the timing of the first performance of something is known only approximately rather than as an exact date.
-
B.
firstUsedAs
Indicates that one entity was the earliest or original thing in which another entity was used or applied.
-
C.
firstUsedAt
Indicates the time or place at which something was initially used or put into operation.
-
D.
firstUsedFor
Indicates that one entity was the earliest or original thing for which another entity was used or applied.
-
E.
firstProminentlyUsedAfter
Indicates that one entity began to be widely or notably used only after the time or event associated with another entity.
- 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_69f01d867608819086bc3e6b4f9de866 |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_6a004a8892c08190bcacb952ad737716 |
completed | May 10, 2026, 9:06 a.m. |
| PD | Predicate disambiguation | batch_6a004a44b4948190be4b3dbfce8da020 |
completed | May 10, 2026, 9:05 a.m. |
Created at: April 28, 2026, 5:06 a.m.