Triple
T29272111
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | USS Franklin (CV-13) |
E742145
|
entity |
| Predicate | locationDuringAttack |
P95771
|
FINISHED |
| Object | Near the Japanese home islands |
—
|
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: Near the Japanese home islands | Statement: [USS Franklin (CV-13), locationDuringAttack, Near the Japanese home islands]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locationDuringAttack Context triple: [USS Franklin (CV-13), locationDuringAttack, Near the Japanese home islands]
-
A.
allegedAssaultLocation
Indicates the place where an assault is claimed or reported to have occurred, without asserting that the assault actually happened.
-
B.
locationDuringConflict
chosen
Indicates that an entity is situated in a specific place for some or all of the duration of a particular conflict or hostilities.
-
C.
attackedIn
Indicates that one entity carried out an attack in the location, context, or time frame specified by another entity or value.
-
D.
terroristAttackLocation
Indicates the place where a terrorist attack occurred or was carried out.
-
E.
stationAttacked
Indicates that an attack has been carried out against a station, targeting it with hostile or destructive actions.
- 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_69f0912124d48190a046642b69407f4c |
completed | April 28, 2026, 10:51 a.m. |
| NER | Named-entity recognition | batch_6a000fda03948190881b7275f249768f |
completed | May 10, 2026, 4:55 a.m. |
| PD | Predicate disambiguation | batch_6a000f607f1881908ee750d58da91690 |
completed | May 10, 2026, 4:53 a.m. |
Created at: April 28, 2026, 12:48 p.m.