Triple
T17862391
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | corbomite bluff |
E446105
|
entity |
| Predicate | claimedProperty |
P129049
|
FINISHED |
| Object | reflects any destructive energy back on attacker |
—
|
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: reflects any destructive energy back on attacker | Statement: [corbomite bluff, claimedProperty, reflects any destructive energy back on attacker]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: claimedProperty Context triple: [corbomite bluff, claimedProperty, reflects any destructive energy back on attacker]
-
A.
claimed
Indicates that an entity has asserted or stated something as true, often without definitive proof or verification.
-
B.
claimedRight
Indicates that an entity asserts or demands a right or entitlement in relation to another entity or resource.
-
C.
claimedAs
Indicates that one entity asserts ownership, authorship, responsibility, or some other form of association over another entity.
-
D.
claimedSee
Indicates that one entity asserted or reported having seen or visually perceived another entity or event.
-
E.
claimedFor
Indicates that one entity has asserted ownership, responsibility, or entitlement over or on behalf of another entity.
- F. None of above. chosen
Provenance (4 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_69d8b9f26f18819089c9e43250bee6ae |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e49790ea148190b7a966812d44f430 |
completed | April 19, 2026, 8:51 a.m. |
| PD | Predicate disambiguation | batch_69e3d8e6d2e88190ad9ef9f8a99f13e6 |
completed | April 18, 2026, 7:17 p.m. |
| PDg | Predicate description generation | batch_69e3db7704588190a34a422421152173 |
completed | April 18, 2026, 7:28 p.m. |
Created at: April 10, 2026, 10:17 a.m.