Triple
T4542597
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | northern elephant seal |
E107569
|
entity |
| Predicate | onLandMovement |
P15695
|
FINISHED |
| Object | undulating body and fore flippers |
—
|
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: undulating body and fore flippers | Statement: [northern elephant seal, onLandMovement, undulating body and fore flippers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: onLandMovement Context triple: [northern elephant seal, onLandMovement, undulating body and fore flippers]
-
A.
usesOnLand
Indicates that one entity employs or operates another entity specifically in a land-based context.
-
B.
isInLand
Indicates that one entity is located within the geographical boundaries of a land area or territory of another entity.
-
C.
hasLandComponent
Indicates that something includes, consists of, or is associated with a land-based part or portion as one of its components.
-
D.
movementLocation
Indicates a relationship where an entity moves to, from, or through a specified location.
-
E.
usesMovement
chosen
Indicates that an entity performs or involves some form of movement as part of its action or behavior.
- 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_69bd43f922788190b7edfa294e39b178 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd57d3be988190bf118c4a87415613 |
completed | March 20, 2026, 2:21 p.m. |
| PD | Predicate disambiguation | batch_69bd5220e40481908ca2d7e2c43d8531 |
completed | March 20, 2026, 1:56 p.m. |
Created at: March 20, 2026, 1:04 p.m.