Triple
T37462584
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tyrantus |
E930954
|
entity |
| Predicate | hasTargetingImmunity |
P100262
|
FINISHED |
| Object | Spells |
—
|
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: Spells | Statement: [Tyrantus, hasTargetingImmunity, Spells]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTargetingImmunity Context triple: [Tyrantus, hasTargetingImmunity, Spells]
-
A.
hasRoleInImmunity
Indicates that an entity functions in or contributes to an immune-related process or mechanism.
-
B.
confersResistanceTo
Indicates that one entity provides or imparts resistance or reduced susceptibility to another entity against a specified agent, condition, or effect.
-
C.
bypassesImmunity
Indicates that one entity is able to circumvent or overcome the protective immunity or defenses of another entity.
-
D.
cannotBeDamagedBy
chosen
Indicates that one entity is immune to harm, injury, or degradation caused by another specified entity or factor.
-
E.
receivedImmunityFrom
Indicates that one entity has been granted protection or exemption (such as legal, medical, or other forms of immunity) by another entity.
- 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_69f76ec1a1148190b0a961f188d621b0 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fbb084760c8190a1554985d3c3cb7a |
completed | May 6, 2026, 9:20 p.m. |
| PD | Predicate disambiguation | batch_69fbadf3cb548190ba3b7514f76b790a |
completed | May 6, 2026, 9:09 p.m. |
Created at: May 3, 2026, 4:17 p.m.