Triple
T9195836
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rachel Watson |
E220703
|
entity |
| Predicate | weaponUsedToKillTomWatson |
P706
|
FINISHED |
| Object | corkscrew |
—
|
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: corkscrew | Statement: [Rachel Watson, weaponUsedToKillTomWatson, corkscrew]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: weaponUsedToKillTomWatson Context triple: [Rachel Watson, weaponUsedToKillTomWatson, corkscrew]
-
A.
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.
-
B.
usedMethodOfKilling
Indicates that one entity employed a particular method or means to carry out a killing of another entity.
-
C.
weaponsUsed
Indicates that one entity employed or utilized another entity as a weapon in carrying out an action or event.
-
D.
hasGasChamber
Indicates that an entity possesses or contains a gas chamber used for administering gas-based processes or executions.
-
E.
usedWeapon
chosen
Indicates that an entity employed a specific weapon as the means or tool to carry out an action or event.
- 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_69ca83e7ba70819088b74866d9da2c30 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69ccd87c3a3c8190b60f19873ef6e1f8 |
completed | April 1, 2026, 8:34 a.m. |
| PD | Predicate disambiguation | batch_69cc660af2408190ae06eb8326e1c64e |
completed | April 1, 2026, 12:25 a.m. |
Created at: March 30, 2026, 7:25 p.m.