Triple
T27688718
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Liu Rong |
E698100
|
entity |
| Predicate | positionEndCause |
P179370
|
FINISHED |
| Object | loss of favor in imperial court |
—
|
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: loss of favor in imperial court | Statement: [Liu Rong, positionEndCause, loss of favor in imperial court]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: positionEndCause Context triple: [Liu Rong, positionEndCause, loss of favor in imperial court]
-
A.
endOfPositionReason
chosen
Indicates the reason or cause for which a position, role, or employment relationship has come to an end.
-
B.
positionStartFor
Indicates the starting position or initial point at which an entity, event, or interval begins relative to another reference.
-
C.
positionOnReason
Indicates that one entity holds a particular stance, justification, or rationale concerning another entity or issue.
-
D.
finishPosition
Indicates the final rank or place an entity achieves in an ordered outcome, such as a race, competition, or sequence of results.
-
E.
conclusionPosition
Indicates the position or location where a conclusion appears within a larger structure, sequence, or document.
- 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_69ef590df8708190af5488f0638e790c |
completed | April 27, 2026, 12:39 p.m. |
| NER | Named-entity recognition | batch_69f7b5ccbda481908fe1945c35e36ce8 |
completed | May 3, 2026, 8:53 p.m. |
| PD | Predicate disambiguation | batch_69f7b4c06f5881908f0b98cad6796478 |
completed | May 3, 2026, 8:49 p.m. |
Created at: April 27, 2026, 2:50 p.m.