Triple
T14738013
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kilo-class submarine |
E346263
|
entity |
| Predicate | acousticCharacteristic |
P9532
|
FINISHED |
| Object | very quiet at low speeds |
—
|
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: very quiet at low speeds | Statement: [Kilo-class submarine, acousticCharacteristic, very quiet at low speeds]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: acousticCharacteristic Context triple: [Kilo-class submarine, acousticCharacteristic, very quiet at low speeds]
-
A.
acousticProperty
chosen
Indicates the relationship between an entity and its sound-related characteristics, such as loudness, pitch, timbre, or other acoustic features.
-
B.
vocalizationCharacteristic
Indicates how an entity’s vocal sounds are characterized, such as their quality, style, or distinctive acoustic features.
-
C.
hasAcousticUse
Indicates that something is used or functions in relation to sound or acoustics.
-
D.
speakerFeatures
Indicates that certain characteristics, attributes, or properties are associated with a speaker in a given context.
-
E.
tonalCharacteristic
Indicates the specific quality or character of a sound’s tone, such as its color, texture, or expressive nuance, in relation to an 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_69d822e6f1c88190bc494d491a907114 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69dec73264848190be23c5f0260cbe13 |
completed | April 14, 2026, 11:01 p.m. |
| PD | Predicate disambiguation | batch_69de8bf9331481909582045cd567d91f |
completed | April 14, 2026, 6:48 p.m. |
Created at: April 10, 2026, 1:29 a.m.