Triple
T26683289
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Orfordness Lighthouse |
E672675
|
entity |
| Predicate | operatedInPastBy |
P15084
|
FINISHED |
| Object | Trinity House |
—
|
NE NERFINISHED |
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: Trinity House | Statement: [Orfordness Lighthouse, operatedInPastBy, Trinity House]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: operatedInPastBy Context triple: [Orfordness Lighthouse, operatedInPastBy, Trinity House]
-
A.
operatedBefore
Indicates that one entity performed an operation or action at an earlier time than another entity.
-
B.
formerlyOperatedBy
chosen
Indicates that an entity was previously operated or managed by another entity, but is no longer under that operation.
-
C.
operatedAmong
Indicates that an entity carried out operations or activities within, or in coordination with, a specified group, set, or collection of other entities.
-
D.
historicallyOperatedIn
Indicates that an entity carried out its activities or operations within a particular location or context during a past time period.
-
E.
historicallyOperatedOn
Indicates that an entity has, at some point in the past, performed an operation or action upon 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_69eecda13424819092b17942c4edf722 |
completed | April 27, 2026, 2:44 a.m. |
| NER | Named-entity recognition | batch_69fd6a1c1c4881908090053bc359b181 |
completed | May 8, 2026, 4:44 a.m. |
| PD | Predicate disambiguation | batch_69fd696f24d8819091033afacbdaadc5 |
completed | May 8, 2026, 4:41 a.m. |
Created at: April 27, 2026, 3:21 a.m.