Triple
T7819472
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Caernarfon, Gwynedd |
E181091
|
entity |
| Predicate | castleConstructionBegan |
P52046
|
FINISHED |
| Object | 1283 |
—
|
LITERAL FINISHED |
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: 1283 | Statement: [Caernarfon, Gwynedd, castleConstructionBegan, 1283]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: castleConstructionBegan Context triple: [Caernarfon, Gwynedd, castleConstructionBegan, 1283]
-
A.
buildingConstructionStart
Indicates the point in time when the construction work on a building begins.
-
B.
monumentConstructionStart
Indicates the date or time when the construction of a monument was begun.
-
C.
castleBuilt
chosen
Indicates that a castle has been constructed or established, typically by a specific agent or during a particular time period.
-
D.
constructionBeganAsFortressIn
Indicates that the construction of something originally began with the purpose or function of serving as a fortress at a specified time or in a specified place.
-
E.
startConstruction
Indicates that an entity initiates the process of building or constructing another entity or structure.
- 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_69ca828153f48190bdb27ac46f8e0745 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69caf97247c481908b18287eb7ee0a53 |
completed | March 30, 2026, 10:30 p.m. |
| PD | Predicate disambiguation | batch_69cae91687788190af9cb7aaa996d291 |
completed | March 30, 2026, 9:20 p.m. |
Created at: March 30, 2026, 4:40 p.m.