Triple
T38641212
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Collie eye anomaly |
E938597
|
entity |
| Predicate | examTimingRecommendation |
P138568
|
FINISHED |
| Object | eye exam at 6–8 weeks of age |
—
|
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: eye exam at 6–8 weeks of age | Statement: [Collie eye anomaly, examTimingRecommendation, eye exam at 6–8 weeks of age]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: examTimingRecommendation Context triple: [Collie eye anomaly, examTimingRecommendation, eye exam at 6–8 weeks of age]
-
A.
examTime
Indicates the scheduled time at which an exam is to take place.
-
B.
examPeriod
chosen
Indicates a time span during which examinations are scheduled to take place.
-
C.
examSession
Indicates a relationship where a specific examination event or period is scheduled or conducted for participants.
-
D.
examType
Indicates the specific category or format of an exam associated with an assessment or testing event.
-
E.
entranceExam
Indicates that an entity is required to pass or participate in an entrance examination as a condition for admission or access to 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_69f76ed948ec81908ce7811608a8f359 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fcdb0de8c08190928cd1323f80ab5c |
completed | May 7, 2026, 6:33 p.m. |
| PD | Predicate disambiguation | batch_69fcd9017dd88190b32a73fe78909740 |
completed | May 7, 2026, 6:25 p.m. |
Created at: May 3, 2026, 4:32 p.m.