Triple
T29599091
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Crown Prince of Bavaria |
E754389
|
entity |
| Predicate | predecessorInRank |
P14604
|
FINISHED |
| Object | King of Bavaria |
—
|
NE NERFINISHED |
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: King of Bavaria | Statement: [Crown Prince of Bavaria, predecessorInRank, King of Bavaria]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: predecessorInRank Context triple: [Crown Prince of Bavaria, predecessorInRank, King of Bavaria]
-
A.
predecessorInSuit
Indicates that one item directly precedes another in an ordered sequence within the same suit or category.
-
B.
predecessorInRole
chosen
Indicates that one entity previously held a particular role or position that was later occupied by another entity.
-
C.
successorRank
Indicates that one entity holds the next higher position or rank in an ordered hierarchy relative to another entity.
-
D.
predecessor
Indicates that one entity comes before another in an ordered sequence or succession.
-
E.
predecessorInRegency
Indicates that one regent directly preceded another in holding regency authority over the same domain or office.
- 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_69f0ef84e5d08190a0df17f5930ceed3 |
completed | April 28, 2026, 5:33 p.m. |
| NER | Named-entity recognition | batch_69f78fd5a6388190bfda4bbb2e222e5b |
completed | May 3, 2026, 6:11 p.m. |
| PD | Predicate disambiguation | batch_69f78e2ac3fc819081a45c6841375c8d |
completed | May 3, 2026, 6:04 p.m. |
Created at: April 28, 2026, 6:20 p.m.