Triple
T36817734
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eärnur |
E909791
|
entity |
| Predicate | successorOfficeHeldBy |
P33240
|
FINISHED |
| Object | Mardil Voronwë |
—
|
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: Mardil Voronwë | Statement: [Eärnur, successorOfficeHeldBy, Mardil Voronwë]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: successorOfficeHeldBy Context triple: [Eärnur, successorOfficeHeldBy, Mardil Voronwë]
-
A.
successorOfficeHolder
chosen
Indicates that one office holder directly follows another in occupying the same official position.
-
B.
successorOfficeTo
Indicates that one office or position directly follows and replaces another in an official sequence or hierarchy.
-
C.
successorOfficeEstablished
Indicates that a new office or position was formally created to replace or succeed a previous one.
-
D.
successorOfficeFunction
Indicates that one office function directly follows and replaces another in an official sequence or organizational structure.
-
E.
successorOfficeInOtherStates
Indicates that one office is the corresponding successor to another office, but only in certain other states or jurisdictions.
- 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_69f76e7dd13c81908c60b05adb49eeb5 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a008c77d4dc8190b342d7407eaf48fa |
completed | May 10, 2026, 1:47 p.m. |
| PD | Predicate disambiguation | batch_6a008c18531c8190bbe883b73e6d023f |
completed | May 10, 2026, 1:46 p.m. |
Created at: May 3, 2026, 4:13 p.m.