Triple
T33157866
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | USS Manhattan |
E848634
|
entity |
| Predicate | armoredAgainst |
P92616
|
FINISHED |
| Object | enemy artillery fire |
—
|
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: enemy artillery fire | Statement: [USS Manhattan, armoredAgainst, enemy artillery fire]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: armoredAgainst Context triple: [USS Manhattan, armoredAgainst, enemy artillery fire]
-
A.
armored
chosen
Indicates that an entity is protected by armor or a defensive covering against damage or attack.
-
B.
armour
Indicates that an entity provides protective covering or defense for another entity.
-
C.
armedAgainst
Indicates that one entity is equipped with weapons or defensive capabilities specifically in preparation for potential conflict with another entity.
-
D.
hasArmorPlating
Indicates that one entity is equipped with or covered by protective armor plating in relation to another entity or context.
-
E.
armourThickness
Indicates the measured thickness of an entity’s protective armor in the context of defense or shielding.
- 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_69f3495b02d08190bb3d366823dffc21 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6dd3cc0648190a275812d6711275a |
completed | May 3, 2026, 5:29 a.m. |
| PD | Predicate disambiguation | batch_69f6d82eaee081908f06a71546315aea |
completed | May 3, 2026, 5:07 a.m. |
Created at: May 1, 2026, 1:28 a.m.