Triple
T8649818
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alpine ibex |
E205069
|
entity |
| Predicate | maleHornDescription |
P78622
|
FINISHED |
| Object | large backward-curving horns with transverse ridges |
—
|
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: large backward-curving horns with transverse ridges | Statement: [Alpine ibex, maleHornDescription, large backward-curving horns with transverse ridges]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: maleHornDescription Context triple: [Alpine ibex, maleHornDescription, large backward-curving horns with transverse ridges]
-
A.
hasHornMaterial
Indicates that an entity’s horn is made of, or composed from, a specified material.
-
B.
maleLength
Indicates that the relationship specifies the length or size measurement of a male individual or male part of an entity.
-
C.
hasHorns
Indicates that an entity possesses horns as a physical feature.
-
D.
maleFeature
chosen
Indicates that the subject possesses a characteristic or attribute typically associated with males.
-
E.
hornSheath
Indicates that one entity is the protective outer covering or sheath surrounding the horn of another entity.
- 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_69ca834e56848190abb0eeaec9dedd32 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc4813d0548190b203e594acc38c8f |
completed | March 31, 2026, 10:17 p.m. |
| PD | Predicate disambiguation | batch_69cc45619460819091e83ffdec99c865 |
completed | March 31, 2026, 10:06 p.m. |
Created at: March 30, 2026, 6:29 p.m.