Triple
T1172148
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tysabri |
E24936
|
entity |
| Predicate | hasHalfLife |
P23051
|
FINISHED |
| Object | approximately 11 days |
—
|
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: approximately 11 days | Statement: [Tysabri, hasHalfLife, approximately 11 days]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasHalfLife Context triple: [Tysabri, hasHalfLife, approximately 11 days]
-
A.
hasMeanLifetime
chosen
Indicates the characteristic average time duration for which an entity, state, or condition persists before it decays, ends, or changes.
-
B.
hasDam
Indicates that a watercourse, reservoir, or similar feature is impounded or controlled by a specific dam.
-
C.
hasSurvivors
Indicates that one or more entities continue to exist or remain alive after a particular event, condition, or incident.
-
D.
hasRemainsOf
Indicates that one entity physically contains, preserves, or is associated with the leftover physical traces or remnants of another entity.
-
E.
isForLife
Indicates that something is intended to last or remain valid for the entire duration of a person’s or entity’s life.
- 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_69a494082a7c819095004f423f294a64 |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4bceb3f188190b8b767380fe5986f |
completed | March 1, 2026, 10:25 p.m. |
| PD | Predicate disambiguation | batch_69a4bb5656948190b0b1d5446ad06005 |
completed | March 1, 2026, 10:19 p.m. |
Created at: March 1, 2026, 7:45 p.m.