Triple
T8355660
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Croagh Patrick |
E196674
|
entity |
| Predicate | summitChapelBuilt |
P36934
|
FINISHED |
| Object | 1905 |
—
|
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: 1905 | Statement: [Croagh Patrick, summitChapelBuilt, 1905]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: summitChapelBuilt Context triple: [Croagh Patrick, summitChapelBuilt, 1905]
-
A.
firstChapelBuilt
Indicates that the subject is the location or entity where the first chapel was constructed or established.
-
B.
mainChurchBuilt
Indicates that the primary church associated with an entity was constructed or established at a particular time or by a particular agent.
-
C.
originalChurchBuilt
Indicates that a particular church building was initially constructed at a given time or by a specified agent, before any later reconstructions or modifications.
-
D.
churchConstructionDate
chosen
Indicates the date on which a church was constructed or originally built.
-
E.
replicaChurchConstructionDate
Indicates the date on which a replica of a church was constructed.
- 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_69ca82f08b348190bfb7881944bbff6f |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb804a344c819089c0a13fe66e3088 |
completed | March 31, 2026, 8:05 a.m. |
| PD | Predicate disambiguation | batch_69cb70ca25548190b0f90c5384e3fb3c |
completed | March 31, 2026, 6:59 a.m. |
Created at: March 30, 2026, 5:59 p.m.