Triple
T22622872
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lazi Church |
E558330
|
entity |
| Predicate | conventMaterial |
P1272
|
FINISHED |
| Object | coral stone |
—
|
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: coral stone | Statement: [Lazi Church, conventMaterial, coral stone]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: conventMaterial Context triple: [Lazi Church, conventMaterial, coral stone]
-
A.
templeMaterial
Indicates that a temple is constructed from, or primarily composed of, a specified material.
-
B.
traditionalMaterial
Indicates that something is made from, incorporates, or is characterized by materials associated with long-established or customary practices.
-
C.
materialOfChapelRuins
Indicates that a specified material was used in the construction of the chapel whose remains or ruins are being described.
-
D.
materialUsed
chosen
Indicates that one entity is made from, incorporates, or utilizes the other entity as its material or substance.
-
E.
featuresMaterialFrom
Indicates that one entity incorporates, contains, or is composed of material originating from another entity.
- 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_69e24545a8e08190bfa7482a2c725ff1 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f16e3ad6f48190b351a52e4b1d9b2d |
completed | April 29, 2026, 2:34 a.m. |
| PD | Predicate disambiguation | batch_69ee62855558819080da946c7b35a160 |
completed | April 26, 2026, 7:07 p.m. |
Created at: April 17, 2026, 3:01 p.m.