Triple
T17771572
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ctenophora |
E443652
|
entity |
| Predicate | bodyConsistency |
P47122
|
FINISHED |
| Object | gelatinous |
—
|
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: gelatinous | Statement: [Ctenophora, bodyConsistency, gelatinous]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bodyConsistency Context triple: [Ctenophora, bodyConsistency, gelatinous]
-
A.
hasConsistency
Indicates that one entity maintains a stable, uniform, or coherent state, behavior, or set of properties in relation to another entity or over time.
-
B.
typicalConsistency
chosen
Indicates that one entity characteristically maintains a regular or expected level of consistency in relation to another entity or context.
-
C.
consistentWith
Indicates that one entity does not contradict and is compatible or in agreement with another entity, condition, or set of constraints.
-
D.
allegedInconsistencyWith
Indicates a claimed or suspected contradiction or mismatch between one thing and another.
-
E.
bodyLevel
Indicates the relative position or height of an entity’s body (or body part) along a vertical or hierarchical scale.
- 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_69d8b9ef17708190bdf7e2adbf14ddc2 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e486005770819085d637279b2334eb |
completed | April 19, 2026, 7:36 a.m. |
| PD | Predicate disambiguation | batch_69e3d8d8e538819084f1584426b41d5e |
completed | April 18, 2026, 7:17 p.m. |
Created at: April 10, 2026, 10:11 a.m.