Triple
T23601314
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | southern elephant seal |
E582763
|
entity |
| Predicate | haulOutBehavior |
P152878
|
FINISHED |
| Object | comes ashore to breed and molt |
—
|
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: comes ashore to breed and molt | Statement: [southern elephant seal, haulOutBehavior, comes ashore to breed and molt]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: haulOutBehavior Context triple: [southern elephant seal, haulOutBehavior, comes ashore to breed and molt]
-
A.
trailBehavior
Indicates how an entity behaves, moves, or leaves traces along a path or trajectory over time.
-
B.
hasTailBehavior
Indicates that an entity exhibits a specific pattern, manner, or type of behavior involving its tail.
-
C.
bootBehavior
Indicates how a system or device behaves during its startup or boot process.
-
D.
inferredBehavior
Indicates that a behavior or action is deduced or predicted for an entity based on indirect evidence, patterns, or reasoning rather than being directly observed.
-
E.
spaceBehavior
Indicates how an entity behaves, operates, or is arranged within a given space or spatial context.
- F. None of above. chosen
Provenance (4 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_69e248faa2788190abb1581742daa6aa |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b0947bd8819097e26643dc257dc0 |
completed | April 29, 2026, 7:17 a.m. |
| PD | Predicate disambiguation | batch_69f118c96a0081908a8ac98ef7e7e60c |
completed | April 28, 2026, 8:30 p.m. |
| PDg | Predicate description generation | batch_69f121cc494081908c987adfcde89b0e |
completed | April 28, 2026, 9:08 p.m. |
Created at: April 17, 2026, 6:43 p.m.