Triple
T36111502
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Downton Abbey (estate) |
E1044509
|
entity |
| Predicate | hasServantCharacters |
P4079
|
FINISHED |
| Object | Mr. Carson |
—
|
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: Mr. Carson | Statement: [Downton Abbey (estate), hasServantCharacters, Mr. Carson]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasServantCharacters Context triple: [Downton Abbey (estate), hasServantCharacters, Mr. Carson]
-
A.
hasServant
chosen
Indicates that one entity has another entity serving it in a subordinate or attendant role.
-
B.
notableServant
Indicates that one entity serves another in a particularly distinguished, prominent, or historically significant capacity.
-
C.
hasEnslavedCharacter
Indicates that one entity has held another entity in a state of slavery or forced servitude.
-
D.
hasPuppetCharacter
Indicates that one entity features, includes, or is associated with a particular puppet character as part of its content or composition.
-
E.
hasFairyCharacters
Indicates that the subject includes or features characters that are fairies.
- 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_69f76e344a4c8190af3858c6d78ba88f |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a0045a7b4c081908e4dedabda7cf790 |
completed | May 10, 2026, 8:45 a.m. |
| PD | Predicate disambiguation | batch_6a0042b148a48190974b173f352e4b7f |
completed | May 10, 2026, 8:32 a.m. |
Created at: May 3, 2026, 4:08 p.m.