Triple
T9860041
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cynoglossidae |
E239685
|
entity |
| Predicate | eyePlacement |
P51923
|
FINISHED |
| Object | both eyes on left side of body |
—
|
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: both eyes on left side of body | Statement: [Cynoglossidae, eyePlacement, both eyes on left side of body]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: eyePlacement Context triple: [Cynoglossidae, eyePlacement, both eyes on left side of body]
-
A.
eyeType
Indicates the specific kind or category of eyes an entity has, such as their form, structure, or visual style.
-
B.
eyeCount
Indicates the number of eyes an entity has.
-
C.
eyeAssociation
Indicates a relationship where one entity is associated with, linked to, or characterized by a particular eye or eye-related feature of another entity.
-
D.
eyeMigration
Indicates the movement or displacement of an eye (or eyes) from one position to another within an organism’s body or visual system.
-
E.
eyeCharacteristic
chosen
Indicates a relationship where an entity possesses a specific attribute, feature, or quality of its eyes.
- 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_69ca84e6493081909cf58c8d42ea856b |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdb3b582cc81909a6d638fe2573c43 |
completed | April 2, 2026, 12:09 a.m. |
| PD | Predicate disambiguation | batch_69cd1d7621d48190aa6a6f34399514b0 |
completed | April 1, 2026, 1:28 p.m. |
Created at: March 30, 2026, 8:35 p.m.