Triple
T3514679
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jormungandr |
E74276
|
entity |
| Predicate | breathEffect |
P48458
|
FINISHED |
| Object | poison that kills Thor after their battle |
—
|
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: poison that kills Thor after their battle | Statement: [Jormungandr, breathEffect, poison that kills Thor after their battle]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: breathEffect Context triple: [Jormungandr, breathEffect, poison that kills Thor after their battle]
-
A.
breathingBehavior
Indicates how an entity performs the act of breathing, such as its pattern, rate, or style of respiration.
-
B.
breathes
Indicates that one entity inhales and exhales air or another gas as part of a respiratory process.
-
C.
visualEffect
Indicates that one entity produces, modifies, or is associated with a particular visual effect on another entity or within a scene.
-
D.
specialEffectsBy
Indicates that the special effects for something (such as a film, scene, or shot) are created or provided by a particular person or entity.
-
E.
placeOfEffect
Indicates the location or setting where an action, event, or effect takes place or is realized.
- 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_69ad85cfb5c881909c9a2edd9d6043cc |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adbc2efa4c8190ac1ca221f3f0eba4 |
completed | March 8, 2026, 6:13 p.m. |
| PD | Predicate disambiguation | batch_69adae10689c8190b7dc6d7daa8295b6 |
completed | March 8, 2026, 5:12 p.m. |
| PDg | Predicate description generation | batch_69adaed74ecc8190b74dc70ab59a3e1c |
completed | March 8, 2026, 5:16 p.m. |
Created at: March 8, 2026, 3:19 p.m.