Triple
T4073227
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Irish grid reference system |
E86697
|
entity |
| Predicate | coordinateFormat |
P53340
|
FINISHED |
| Object | alphanumeric grid reference |
—
|
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: alphanumeric grid reference | Statement: [Irish grid reference system, coordinateFormat, alphanumeric grid reference]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: coordinateFormat Context triple: [Irish grid reference system, coordinateFormat, alphanumeric grid reference]
-
A.
coordinatesMode
Indicates that one entity specifies or controls the coordinate system or reference frame used to interpret the spatial data of another entity.
-
B.
coordinateSymbols
Indicates a relationship where one symbol is aligned or matched with another symbol in a coordinated or corresponding way.
-
C.
coordinateSystem
Indicates that one entity defines or uses a particular spatial or reference coordinate system in relation to another entity.
-
D.
addressFormat
Indicates the standardized structure or pattern in which an address’s components are arranged and written.
-
E.
coordinates
Indicates that one entity organizes, directs, or harmonizes the actions or efforts of another entity or group to achieve a unified outcome.
- F. None of above. chosen
Provenance (4 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_69aed93ebe448190a1f1686e28740ac9 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefc22be988190a2b6575d4f5e0f7b |
completed | March 9, 2026, 4:58 p.m. |
| PD | Predicate disambiguation | batch_69aef9061d2481908307cafc9e9b32c0 |
completed | March 9, 2026, 4:44 p.m. |
| PDg | Predicate description generation | batch_69aefa5c52648190b001027f4dba75cb |
completed | March 9, 2026, 4:50 p.m. |
Created at: March 9, 2026, 3:38 p.m.