Triple
T9966417
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | marbled murrelet |
E195693
|
entity |
| Predicate | nonBreedingPlumage |
P76069
|
FINISHED |
| Object | blackish upperparts and white underparts |
—
|
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: blackish upperparts and white underparts | Statement: [marbled murrelet, nonBreedingPlumage, blackish upperparts and white underparts]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: nonBreedingPlumage Context triple: [marbled murrelet, nonBreedingPlumage, blackish upperparts and white underparts]
-
A.
nonBreedingPlumageColor
chosen
Indicates the coloration an organism displays in its non-breeding (non-reproductive) plumage phase.
-
B.
plumageFeature
Indicates a relationship where a specific characteristic or attribute is associated with an entity’s plumage (feathers).
-
C.
plumageColorCommon
Indicates that two entities share the same typical or most frequently observed plumage color.
-
D.
maleBreedingPlumageFeature
Indicates that the relationship involves a physical or visual characteristic specifically associated with a male’s breeding-season plumage.
-
E.
malePlumage
Indicates that the specified plumage belongs to or characterizes the male individual of a species.
- 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_69ca82ebd1288190912f9e4482d1fa35 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdb71dc50081909329722dc087c9f6 |
completed | April 2, 2026, 12:23 a.m. |
| PD | Predicate disambiguation | batch_69cd1d9ae19c819099fb3635e57c79be |
completed | April 1, 2026, 1:28 p.m. |
Created at: March 30, 2026, 8:47 p.m.