Triple
T38108484
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Physician's Tale |
E951585
|
entity |
| Predicate | frameSpeakerOccupation |
P102156
|
FINISHED |
| Object | physician |
—
|
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: physician | Statement: [The Physician's Tale, frameSpeakerOccupation, physician]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: frameSpeakerOccupation Context triple: [The Physician's Tale, frameSpeakerOccupation, physician]
-
A.
hasFrameSpeakerOccupation
chosen
Indicates that a frame’s speaker is associated with a particular occupation or professional role.
-
B.
frameSpeakerTrait
Indicates that one entity characterizes or portrays a speaker as having a particular trait or quality.
-
C.
pointHasSpeaker
Indicates that a specific point (e.g., in time, space, or discourse) is associated with a particular speaker.
-
D.
primarySpeakersOccupation
Indicates the main or most common occupation held by the speakers of a given language.
-
E.
hasSpeakerIn
Indicates that an event, work, or communication features a particular entity serving as its speaker.
- 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_69f76f065ed08190bdfb1b6d817f5b39 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fc4748843c8190931432653be4890c |
completed | May 7, 2026, 8:03 a.m. |
| PD | Predicate disambiguation | batch_69fc45646ce481908caf292ff9f06e15 |
completed | May 7, 2026, 7:55 a.m. |
Created at: May 3, 2026, 4:21 p.m.