Triple
T32821666
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Donegal Town |
E839449
|
entity |
| Predicate | castleRebuiltBy |
P52047
|
FINISHED |
| Object | Sir Basil Brooke |
—
|
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: Sir Basil Brooke | Statement: [Donegal Town, castleRebuiltBy, Sir Basil Brooke]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: castleRebuiltBy Context triple: [Donegal Town, castleRebuiltBy, Sir Basil Brooke]
-
A.
castleRestoredBy
chosen
Indicates that a castle has been repaired, renovated, or returned to a previous condition through the efforts or actions of a specified agent.
-
B.
castleBuilt
Indicates that a castle has been constructed or established, typically by a specific agent or during a particular time period.
-
C.
castleBuiltOf
Indicates that a castle is constructed primarily from a specified material.
-
D.
castleBuiltOn
Indicates that a castle is constructed directly on top of, or firmly established upon, a particular surface, structure, or geographical feature.
-
E.
castleBuiltFor
Indicates that a castle was constructed specifically for the benefit, use, or commission of a particular person, group, or purpose.
- 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_69f3493df9008190a8f5d843dcd77704 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6ce6d659881909ddcec1d2966e020 |
completed | May 3, 2026, 4:26 a.m. |
| PD | Predicate disambiguation | batch_69f6cc1667a48190b42684f6ec22dae9 |
completed | May 3, 2026, 4:16 a.m. |
Created at: May 1, 2026, 1:15 a.m.