Triple
T37214146
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Earl of Ellenborough |
E922688
|
entity |
| Predicate | hasFirstHolderRole |
P3904
|
FINISHED |
| Object | Governor-General of India |
—
|
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: Governor-General of India | Statement: [Earl of Ellenborough, hasFirstHolderRole, Governor-General of India]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFirstHolderRole Context triple: [Earl of Ellenborough, hasFirstHolderRole, Governor-General of India]
-
A.
hasFirstHolder
chosen
Indicates that an entity is associated with the earliest or original holder (e.g., owner, position-bearer, or title-holder) of something.
-
B.
hasPositionHolderRole
Indicates that an entity holds or occupies a specific position, office, or role within an organization or structure.
-
C.
hasCurrentHolder
Indicates that a specified entity is the present holder, possessor, or occupant of another entity (such as a position, title, asset, or object).
-
D.
hasPreviousHolder
Indicates that an entity was formerly held, occupied, or possessed by another specified entity before the current one.
-
E.
hasHolderRight
Indicates that one entity possesses a legal or formal right over another entity or resource.
- 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_69f76ea6f5288190b8d9988f613811c0 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a004a8892c08190bcacb952ad737716 |
completed | May 10, 2026, 9:06 a.m. |
| PD | Predicate disambiguation | batch_6a004a44b4948190be4b3dbfce8da020 |
completed | May 10, 2026, 9:05 a.m. |
Created at: May 3, 2026, 4:15 p.m.