Triple
T35540381
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | RMS Carpathia |
E1027042
|
entity |
| Predicate | landedSurvivorsAt |
P87000
|
FINISHED |
| Object | New York City |
—
|
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: New York City | Statement: [RMS Carpathia, landedSurvivorsAt, New York City]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: landedSurvivorsAt Context triple: [RMS Carpathia, landedSurvivorsAt, New York City]
-
A.
survivorsLandingPlace
chosen
Indicates the location where survivors arrived or were brought after an incident or event.
-
B.
survivorsOnRaft
Indicates that certain individuals remain alive and present together on a specific raft after a hazardous or catastrophic event.
-
C.
madeLandfallAt
Indicates that a storm or similar weather system has come ashore at a specific geographic location.
-
D.
madeLandfallOn
Indicates that a storm or similar weather system has come ashore and first reached land at a specific location or on a specific date.
-
E.
landedNear
Indicates that one entity has come to rest on a surface or location in close proximity to another specified entity or reference point.
- 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_69f76e008ba08190927acd8e5e0344c8 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f79a54aa3c8190b2bb5d790b2d42d4 |
completed | May 3, 2026, 6:56 p.m. |
| PD | Predicate disambiguation | batch_69f7961970408190b669cc556e30a608 |
completed | May 3, 2026, 6:38 p.m. |
Created at: May 3, 2026, 4:04 p.m.