Triple
T37008399
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Navassa Island Light |
E915868
|
entity |
| Predicate | operatorAtConstruction |
P62878
|
FINISHED |
| Object | United States Lighthouse Service |
E12619
|
NE 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: United States Lighthouse Service | Statement: [Navassa Island Light, operatorAtConstruction, United States Lighthouse Service]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: operatorAtConstruction Context triple: [Navassa Island Light, operatorAtConstruction, United States Lighthouse Service]
-
A.
operatorDuringConstruction
chosen
Indicates that an entity serves as the operator of another entity specifically during its construction phase.
-
B.
operatorAtOpening
Indicates that an operator is present and on duty at the time of an opening event.
-
C.
operatorAtPeak
Indicates that an operator is present and performing their role at the peak or highest point of a process, structure, or operational cycle.
-
D.
operatorLater
Indicates that one operator or operation occurs at a later time than another in a temporal ordering.
-
E.
constructedDuring
Indicates that one entity was built or created within the time period defined by another entity or event.
- F. None of above.
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_69f76e90ed548190b187d2475f5c807d |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a01e3a2d0e08190a7d5622920dc56e6 |
completed | May 11, 2026, 2:11 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a3e576ecbb8819088c982b3775b7524 |
completed | June 26, 2026, 10:41 a.m. |
| PD | Predicate disambiguation | batch_6a01e3013e7881909f0cdca25a53c009 |
completed | May 11, 2026, 2:09 p.m. |
Created at: May 3, 2026, 4:14 p.m.