Triple
T23066220
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NOAA research vessel Pisces |
E575048
|
entity |
| Predicate | hasRadioCallsign |
P1565
|
FINISHED |
| Object | WTDL |
—
|
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: WTDL | Statement: [NOAA research vessel Pisces, hasRadioCallsign, WTDL]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: WTDL Context triple: [NOAA research vessel Pisces, hasRadioCallsign, WTDL]
-
A.
WTDL
chosen
WTDL is the radio callsign assigned to the NOAA research vessel Pisces, used for its identification in maritime communications.
-
B.
WDTD
WDTD is the Warning Decision Training Division, a U.S. National Weather Service unit that develops and delivers training to improve severe weather forecasting and warning operations.
-
C.
WADT
WADT is the ICAO airport code for Tambolaka Airport, a regional airport serving the island of Sumba in Indonesia.
-
D.
TDL
TDL is the Indian Railways station code for Tundla Junction, a major railway junction in Uttar Pradesh, India.
-
E.
WTDH
WTDH is the radio callsign assigned to the NOAA Ship Okeanos Explorer, a U.S. research vessel dedicated to deep-ocean exploration.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e245bd6e4c8190bb8942245b68cad5 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f189a3e39481909cad356ad0bb3ee6 |
completed | April 29, 2026, 4:31 a.m. |
Created at: April 17, 2026, 3:55 p.m.