Triple
T3112074
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Port Arthur |
E64973
|
entity |
| Predicate | opponentFleetStatus |
P21295
|
FINISHED |
| Object | anchored in harbor |
—
|
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: anchored in harbor | Statement: [Battle of Port Arthur, opponentFleetStatus, anchored in harbor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: opponentFleetStatus Context triple: [Battle of Port Arthur, opponentFleetStatus, anchored in harbor]
-
A.
opposingForcesStatus
Indicates the current state or condition of two or more forces that are in conflict or opposition to each other.
-
B.
navalPowerStatus
Indicates the relative strength, capability, or strategic standing of an entity’s naval forces compared to others or to defined benchmarks.
-
C.
statusOfOtherShips
chosen
Indicates the relationship that reports or reflects the current conditions or states (such as position, readiness, or operational status) of other ships.
-
D.
otherShipsInFleet
Indicates that the subject ship and the object ship are distinct members of the same fleet.
-
E.
navalFleet
Indicates a relationship where multiple naval vessels are organized and operate together as a coordinated maritime military force.
- 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_69ad857eeaf48190b34ebfdaa7a264cf |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada43b0b3c8190a828c9cfcf730ed9 |
completed | March 8, 2026, 4:30 p.m. |
| PD | Predicate disambiguation | batch_69ad9df25d4c81908ff0f6cff55d0563 |
completed | March 8, 2026, 4:04 p.m. |
Created at: March 8, 2026, 3:04 p.m.