Triple
T21463491
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | In Two Minds |
E529531
|
entity |
| Predicate | firstBroadcastAs |
P113421
|
FINISHED |
| Object | episode of The Wednesday Play |
—
|
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: episode of The Wednesday Play | Statement: [In Two Minds, firstBroadcastAs, episode of The Wednesday Play]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstBroadcastAs Context triple: [In Two Minds, firstBroadcastAs, episode of The Wednesday Play]
-
A.
firstBroadcastAsPartOf
Indicates that an entity’s first broadcast occurred as a component or segment within a larger program, series, or event rather than as a standalone broadcast.
-
B.
firstBroadcastFor
chosen
Indicates that one entity is the initial or earliest broadcast instance associated with another entity (such as a program, episode, or event).
-
C.
firstBroadcastBy
Indicates that one entity is the original broadcaster or channel that first aired the other entity (such as a program, event, or content).
-
D.
firstBroadcast
Indicates the date or event of the initial public transmission or airing of a program, signal, or content.
-
E.
firstBroadcastTime
Indicates the date and time at which something (typically a program or content) was first broadcast.
- 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_69e0c458133481908ae8b41a12c4edec |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9e9efdb188190be79b72e1bd18860 |
completed | April 23, 2026, 9:44 a.m. |
| PD | Predicate disambiguation | batch_69e631df1b38819088d3604854e697b4 |
completed | April 20, 2026, 2:02 p.m. |
Created at: April 16, 2026, 6:09 p.m.