Triple
T10104481
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dungeness crab |
E216282
|
entity |
| Predicate | carapaceWidth |
P79493
|
FINISHED |
| Object | up to about 20 centimeters |
—
|
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: up to about 20 centimeters | Statement: [Dungeness crab, carapaceWidth, up to about 20 centimeters]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: carapaceWidth Context triple: [Dungeness crab, carapaceWidth, up to about 20 centimeters]
-
A.
carapaceLength
Indicates the measured length of an organism’s carapace from a defined anatomical reference point.
-
B.
carapaceLengthRange
Indicates the minimum and maximum measured lengths of an organism’s carapace within a specified context or dataset.
-
C.
averageCarapaceWidth
Indicates the measured mean width of an organism’s carapace across a set of individuals or observations.
-
D.
carapaceLengthMax
Indicates the maximum recorded or allowed length of an organism’s carapace in a given context.
-
E.
maximumCarapaceWidth
chosen
Indicates the greatest measured width of an organism’s carapace within a given context or dataset.
- 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_69ca83d039f08190b9d10363221c69fb |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cdd09c961081909848acec4438c300 |
completed | April 2, 2026, 2:12 a.m. |
| PD | Predicate disambiguation | batch_69cd4b9b853c8190a2af993ce9b21309 |
completed | April 1, 2026, 4:45 p.m. |
Created at: March 30, 2026, 9:03 p.m.