Triple
T20270619
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Belgian Shepherd Dog |
E499081
|
entity |
| Predicate | heightFemale |
P60924
|
FINISHED |
| Object | approximately 56–62 cm at the withers |
—
|
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: approximately 56–62 cm at the withers | Statement: [Belgian Shepherd Dog, heightFemale, approximately 56–62 cm at the withers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: heightFemale Context triple: [Belgian Shepherd Dog, heightFemale, approximately 56–62 cm at the withers]
-
A.
femaleHeight
Indicates the height measurement associated specifically with a female individual.
-
B.
averageFemaleHeight
Indicates the typical or mean height value observed among female individuals in a given group or population.
-
C.
femaleHeightRangeCm
chosen
Indicates the range of heights, measured in centimeters, that is associated with female individuals.
-
D.
mastHeight
Indicates the height of a mast relative to a referenced object or measurement standard.
-
E.
averageBodyLengthFemale
Indicates the typical or mean body length measured specifically for female individuals of a given group or 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_69da6275fa6c8190952924930adee150 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e675dd7c58819095bbf4baeda04d6a |
completed | April 20, 2026, 6:52 p.m. |
| PD | Predicate disambiguation | batch_69e55b1e5e1c8190ba8a5544b1db9e1d |
completed | April 19, 2026, 10:45 p.m. |
Created at: April 11, 2026, 11:42 p.m.