Triple
T27376637
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dr. Amelia Shepherd |
E691091
|
entity |
| Predicate | professionRank |
P34138
|
FINISHED |
| Object | Head of Neurosurgery |
—
|
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: Head of Neurosurgery | Statement: [Dr. Amelia Shepherd, professionRank, Head of Neurosurgery]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: professionRank Context triple: [Dr. Amelia Shepherd, professionRank, Head of Neurosurgery]
-
A.
roleInRanking
Indicates that an entity holds a specific position or function within a particular ranking or ordered list.
-
B.
rankWithinOrganization
chosen
Indicates the relative hierarchical position or level an entity holds within a specific organization.
-
C.
establishedRank
Indicates that a stable or officially recognized hierarchical position or level has been assigned to an entity relative to others.
-
D.
partnerRank
Indicates the relative status or level assigned to a partner within a partnership or collaboration hierarchy.
-
E.
classRank
Indicates the relative academic standing or position of an entity within a class or cohort based on performance or criteria.
- 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_69ef52022538819081f873d0c84a6dd6 |
completed | April 27, 2026, 12:09 p.m. |
| NER | Named-entity recognition | batch_69f6691f5e188190b12c7b2eb729a45e |
completed | May 2, 2026, 9:14 p.m. |
| PD | Predicate disambiguation | batch_69f66598d6008190a7ca8ff80399fd34 |
completed | May 2, 2026, 8:59 p.m. |
Created at: April 27, 2026, 12:21 p.m.