Triple
T13313704
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | wedge-tailed eagle |
E317134
|
entity |
| Predicate | legCovering |
P18325
|
FINISHED |
| Object | feathered tarsi |
—
|
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: feathered tarsi | Statement: [wedge-tailed eagle, legCovering, feathered tarsi]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: legCovering Context triple: [wedge-tailed eagle, legCovering, feathered tarsi]
-
A.
bodyCovering
chosen
Indicates the type of external covering or surface (such as skin, fur, feathers, or scales) that characterizes an entity’s body.
-
B.
bodyCoverage
Indicates the extent or proportion of an entity’s body that is covered by another substance, material, or feature.
-
C.
bandCoverage
Indicates the range or extent of frequencies, wavelengths, or channels that a particular band encompasses or provides.
-
D.
bedCover
Indicates that one object functions as a covering placed over a bed.
-
E.
typeOfOrganCovered
Indicates the specific organ or body part that is protected or covered by something (such as a device, garment, or material).
- 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_69d806b40ab4819094adf6c374f4811a |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d99cfdc9388190af1fdd3cd4717bd8 |
completed | April 11, 2026, 12:59 a.m. |
| PD | Predicate disambiguation | batch_69d98f6babd88190a5d529df9584b9a4 |
completed | April 11, 2026, 12:01 a.m. |
Created at: April 9, 2026, 9:29 p.m.