Triple
T35991842
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | USS Spiegel Grove |
E1040866
|
entity |
| Predicate | initialSinkingOrientation |
P131949
|
FINISHED |
| Object | on her starboard side |
—
|
LITERAL 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: on her starboard side | Statement: [USS Spiegel Grove, initialSinkingOrientation, on her starboard side]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: initialSinkingOrientation Context triple: [USS Spiegel Grove, initialSinkingOrientation, on her starboard side]
-
A.
initialAttitude
Indicates the starting stance, feeling, or disposition one entity holds toward another or toward a situation before any interaction or change occurs.
-
B.
initialPosition
chosen
Indicates the original or starting location of an entity before any movement or change in position occurs.
-
C.
oceanOrientation
Indicates the directional alignment or facing of something relative to an ocean.
-
D.
earlyOrientation
Indicates that one entity is oriented, aligned, or scheduled earlier in time relative to another reference point or event.
-
E.
seaOrientation
Indicates the directional relationship of something relative to the sea or coastline (e.g., which way it faces or is aligned).
- 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_69f76e29084c819083987b828d414de7 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69fd09840ea88190a2e6d7e577ade717 |
completed | May 7, 2026, 9:52 p.m. |
| PD | Predicate disambiguation | batch_69fd064c49988190afadddbd04d7cb94 |
completed | May 7, 2026, 9:38 p.m. |
Created at: May 3, 2026, 4:07 p.m.