Triple
T4808883
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hugo Drax |
E107015
|
entity |
| Predicate | weaponInFilm |
P9724
|
FINISHED |
| Object | nerve gas derived from a rare orchid |
—
|
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: nerve gas derived from a rare orchid | Statement: [Hugo Drax, weaponInFilm, nerve gas derived from a rare orchid]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: weaponInFilm Context triple: [Hugo Drax, weaponInFilm, nerve gas derived from a rare orchid]
-
A.
weapon
Indicates that one entity is used as a weapon by, or serves as the weapon of, another entity.
-
B.
weaponsUsed
Indicates that one entity employed or utilized another entity as a weapon in carrying out an action or event.
-
C.
weaponUsedAgainst
Indicates that a particular weapon or instrument is employed in an act of aggression, attack, or harm directed toward a specific target or entity.
-
D.
involvesWeaponType
chosen
Indicates that the relationship or action includes the use, presence, or association of a specific type or category of weapon.
-
E.
typicalWeapon
Indicates that the object is a weapon commonly or characteristically used by the subject.
- 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_69bd43f779448190b92885cb70abb6c2 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6ff981fc819080d4466c6fe06cf3 |
completed | March 20, 2026, 4:04 p.m. |
| PD | Predicate disambiguation | batch_69bd6c1c43a48190a65e56b1624a2339 |
completed | March 20, 2026, 3:47 p.m. |
Created at: March 20, 2026, 1:23 p.m.