Triple
T8303603
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hôpital Saint-Louis |
E194404
|
entity |
| Predicate | notableSpeciality |
P34707
|
FINISHED |
| Object | infectious diseases |
—
|
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: infectious diseases | Statement: [Hôpital Saint-Louis, notableSpeciality, infectious diseases]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableSpeciality Context triple: [Hôpital Saint-Louis, notableSpeciality, infectious diseases]
-
A.
notableFor
Indicates that an entity is especially recognized or distinguished for a particular quality, achievement, characteristic, or role.
-
B.
notableFeatureOn
Indicates that one entity is a prominent or distinguishing feature located on or part of another entity.
-
C.
notableSingle
Indicates that the subject is particularly recognized or distinguished for one specific, individual instance (such as a single work, event, or achievement).
-
D.
subjectNotableFor
chosen
Indicates that the subject is especially recognized or distinguished for a particular attribute, achievement, role, or characteristic.
-
E.
notableFeat
Indicates that an entity is recognized for having achieved or performed a particularly significant or distinguished feat.
- 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_69ca82e613e88190bf8139669bbd0d53 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb7e8b9f6081909100d1da8a078616 |
completed | March 31, 2026, 7:58 a.m. |
| PD | Predicate disambiguation | batch_69cb70bb3a708190bc705222092da614 |
completed | March 31, 2026, 6:59 a.m. |
Created at: March 30, 2026, 5:53 p.m.