Triple
T27173327
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Exxon Valdez |
E682975
|
entity |
| Predicate | homePortAtTimeOfAccident |
P3150
|
FINISHED |
| Object | San Francisco, California |
—
|
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: San Francisco, California | Statement: [Exxon Valdez, homePortAtTimeOfAccident, San Francisco, California]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: homePortAtTimeOfAccident Context triple: [Exxon Valdez, homePortAtTimeOfAccident, San Francisco, California]
-
A.
laterHomePort
Indicates that one location served as the subsequent or later home port of a vessel or entity after an earlier home port.
-
B.
homePort
chosen
Indicates that a vessel or mobile entity is based at, registered to, or primarily operates from a particular port or harbor.
-
C.
homeportAsNOAA
Indicates that a vessel’s designated home port is assigned or recognized specifically as a NOAA (National Oceanic and Atmospheric Administration) home port.
-
D.
intendedDestinationAtAccident
Indicates that a location was the destination an entity was heading toward at the time an accident occurred.
-
E.
originAirportAtTimeOfCrash
Indicates the airport from which an aircraft departed at the specific time when the crash occurred.
- 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_69eefad086808190ab89816c0c300476 |
completed | April 27, 2026, 5:57 a.m. |
| NER | Named-entity recognition | batch_69f62549039c8190af7159d07416c985 |
completed | May 2, 2026, 4:24 p.m. |
| PD | Predicate disambiguation | batch_69f61b40f02081909bd9c3ea73249163 |
completed | May 2, 2026, 3:41 p.m. |
Created at: April 27, 2026, 9:24 a.m.