Triple
T33391118
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hemitripterus |
E855046
|
entity |
| Predicate | bottomTypePreference |
P16678
|
FINISHED |
| Object | soft substrates |
—
|
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: soft substrates | Statement: [Hemitripterus, bottomTypePreference, soft substrates]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bottomTypePreference Context triple: [Hemitripterus, bottomTypePreference, soft substrates]
-
A.
bottomType
Indicates that the subject entity is classified as a bottom-level or most specific type within a type hierarchy.
-
B.
hasBottomness
Indicates that one entity occupies or represents the lower or bottom position relative to another entity.
-
C.
bottomStripePosition
Indicates the vertical placement of the bottom stripe relative to a reference frame or object.
-
D.
substratePreference
chosen
Indicates a relationship where an entity tends to occur on, grow in, or utilize a particular physical material or medium as its preferred substrate.
-
E.
biteLocationPreference
Indicates a tendency or pattern regarding where on a target an entity prefers to bite.
- 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_69f3496d54048190a1cb91fdd7caa6ea |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f6f38159d08190980ad639e08f00f4 |
completed | May 3, 2026, 7:04 a.m. |
| PD | Predicate disambiguation | batch_69f6e3d7bee48190b94e0beb48a1d7fa |
completed | May 3, 2026, 5:57 a.m. |
Created at: May 1, 2026, 1:35 a.m.