Triple
T19582871
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Moon Is a Harsh Mistress |
E490038
|
entity |
| Predicate | serializationForm |
P62614
|
FINISHED |
| Object | serial |
—
|
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: serial | Statement: [The Moon Is a Harsh Mistress, serializationForm, serial]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: serializationForm Context triple: [The Moon Is a Harsh Mistress, serializationForm, serial]
-
A.
serializationFormatFor
Indicates the data serialization format used to encode or represent a given resource or entity.
-
B.
serialized
Indicates that one entity has been converted into a sequential, storable or transmittable data format representing its structure or state.
-
C.
serializedIn
chosen
Indicates that something is published or presented in sequential installments within a larger medium or series.
-
D.
encodingForm
Indicates the specific format or scheme used to encode information or data in a representation or communication.
-
E.
originalSerialization
Indicates that one entity is the initial or source serialized form from which another serialized representation is derived.
- 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_69d8e8dd9374819098e36349b3211663 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e6404f34b081908aeb9cc9a5ddf539 |
completed | April 20, 2026, 3:03 p.m. |
| PD | Predicate disambiguation | batch_69e514dbdb988190b55931a8138c73e7 |
completed | April 19, 2026, 5:46 p.m. |
Created at: April 10, 2026, 1:42 p.m.