Triple
T12355628
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wall of the Missing |
E294604
|
entity |
| Predicate | memorialTypeOfDeath |
P68810
|
FINISHED |
| Object | missing in action |
—
|
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: missing in action | Statement: [Wall of the Missing, memorialTypeOfDeath, missing in action]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: memorialTypeOfDeath Context triple: [Wall of the Missing, memorialTypeOfDeath, missing in action]
-
A.
memorialType
Indicates the specific kind or category of memorial associated with an entity (e.g., plaque, statue, monument).
-
B.
memorializesDeathsDuring
Indicates a relationship in which something serves as a memorial specifically for deaths that occurred during a particular event, period, or circumstance.
-
C.
causeOfDeathsCommemorated
chosen
Indicates that one entity is the cause of the deaths that are formally remembered or honored by another entity.
-
D.
memorialWork
Indicates that one entity is a commemorative work (such as a monument, plaque, or artwork) created to honor or remember another entity.
-
E.
memorialRole
Indicates that an entity holds a specific role, capacity, or function in relation to a memorial or commemorative context.
- 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_69d6ab6ccbec8190b09e2d357aa80064 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d942a2d6e08190a13c7ff89af09354 |
completed | April 10, 2026, 6:34 p.m. |
| PD | Predicate disambiguation | batch_69d93ecf6b548190a394b6b56a0c1c68 |
completed | April 10, 2026, 6:17 p.m. |
Created at: April 8, 2026, 9:54 p.m.