Triple
T3621831
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Once Upon a Mattress |
E76743
|
entity |
| Predicate | productionMedium |
P5765
|
FINISHED |
| Object | live theatre |
—
|
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: live theatre | Statement: [Once Upon a Mattress, productionMedium, live theatre]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: productionMedium Context triple: [Once Upon a Mattress, productionMedium, live theatre]
-
A.
notableRecordingMedium
Indicates that an entity is notably recorded, documented, or expressed using a particular medium or format.
-
B.
primaryMedium
chosen
Indicates the main material, format, or channel through which something is created, expressed, or communicated.
-
C.
primaryBroadcastMedium
Indicates the main communication channel or platform through which something (such as content, information, or a message) is originally transmitted or distributed.
-
D.
tradeMedium
Indicates that one entity serves as the medium or instrument through which another entity conducts trade or exchange transactions.
-
E.
filmMedium
Indicates the physical or technical format (such as film stock, digital, or video) in which a film is recorded or presented.
- 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_69ad85dae2fc81908d1ceadbc6af0089 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc2bb12cc8190bd67597cf3b66a3a |
completed | March 8, 2026, 6:40 p.m. |
| PD | Predicate disambiguation | batch_69adb83f1e4c8190ab501c1c05b14c08 |
completed | March 8, 2026, 5:56 p.m. |
Created at: March 8, 2026, 3:23 p.m.