Triple
T17127132
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Isopoda |
E415624
|
entity |
| Predicate | hasThoracicSegments |
P124647
|
FINISHED |
| Object | seven pairs of thoracic segments with legs |
—
|
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: seven pairs of thoracic segments with legs | Statement: [Isopoda, hasThoracicSegments, seven pairs of thoracic segments with legs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasThoracicSegments Context triple: [Isopoda, hasThoracicSegments, seven pairs of thoracic segments with legs]
-
A.
hasThoracicLegs
chosen
Indicates that an entity possesses legs located in the thoracic (mid-body) region.
-
B.
hasSpines
Indicates that one entity possesses or is characterized by spines or spine-like structures.
-
C.
hasAbdominalLimbs
Indicates that an entity possesses limbs located on or extending from the abdominal region.
-
D.
hasLimbs
Indicates that an entity possesses one or more limbs as physical appendages.
-
E.
analFinSpinesCount
Indicates the number of spines present in an organism’s anal fin.
- 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_69d886d090cc8190a39cb94992586905 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3f027a3d081908fc1134b50db3d45 |
completed | April 18, 2026, 8:57 p.m. |
| PD | Predicate disambiguation | batch_69e3830192ac819091344a9e5a36c8c9 |
completed | April 18, 2026, 1:11 p.m. |
Created at: April 10, 2026, 5:36 a.m.