Triple
T7329343
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Halfway Rock Light |
E168957
|
entity |
| Predicate | ARLHSNumber |
P8195
|
FINISHED |
| Object | ARLHS USA-364 |
—
|
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: ARLHS USA-364 | Statement: [Halfway Rock Light, ARLHSNumber, ARLHS USA-364]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ARLHSNumber Context triple: [Halfway Rock Light, ARLHSNumber, ARLHS USA-364]
-
A.
UAXNumber
Indicates a relationship where an entity is associated with a specific UAX (User Access/Authorization/Account/Unit Assignment, etc.) identification number used for tracking or reference.
-
B.
OJNumber
Indicates that an entity is assigned a specific official journal or case identification number used for tracking or reference.
-
C.
number
chosen
Indicates that one entity is associated with a specific numerical value or count in relation to another entity or context.
-
D.
valueOfL
Indicates that one entity represents the numerical or quantitative value associated with another entity, typically in a specific context or measurement.
-
E.
arithmetic
Indicates a relationship where one entity performs or represents a mathematical operation (such as addition, subtraction, multiplication, or division) involving one or more other entities.
- 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_69c68a54cacc81908e3b773441f19566 |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f0a9c0f081909218560d8a4f4995 |
completed | March 27, 2026, 9:03 p.m. |
| PD | Predicate disambiguation | batch_69c6e77230048190b2c29ca6b3a65b8e |
completed | March 27, 2026, 8:24 p.m. |
Created at: March 27, 2026, 3:03 p.m.