Triple
T27214448
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Simon (The Walking Dead) |
E684097
|
entity |
| Predicate | walkerFormUsedAs |
P162259
|
FINISHED |
| Object | warning on Sanctuary fence |
—
|
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: warning on Sanctuary fence | Statement: [Simon (The Walking Dead), walkerFormUsedAs, warning on Sanctuary fence]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: walkerFormUsedAs Context triple: [Simon (The Walking Dead), walkerFormUsedAs, warning on Sanctuary fence]
-
A.
formaWalki
Indicates a relationship where an entity is associated with, or characterized by, a particular form or style of combat.
-
B.
walkOffType
Indicates the specific way in which a walk-off (a game-ending play or event) occurs or is classified.
-
C.
walkThrough
Indicates moving through or along the interior or extent of something, typically traversing a space or environment from one side or point to another.
-
D.
walkOff
Indicates that an entity departs or leaves a place or situation by walking away from it.
-
E.
usesForm
Indicates that one entity employs, applies, or operates through a particular form, format, or structured representation of something.
- 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_69eefad339a08190aeacb2a198f1a39b |
completed | April 27, 2026, 5:57 a.m. |
| NER | Named-entity recognition | batch_69f6261bcb988190ab516bee317a881c |
completed | May 2, 2026, 4:28 p.m. |
| PD | Predicate disambiguation | batch_69f620e38aec8190bb184edcdbd6da64 |
completed | May 2, 2026, 4:05 p.m. |
| PDg | Predicate description generation | batch_69f622a8fe7c819096e8a43db263a423 |
completed | May 2, 2026, 4:13 p.m. |
Created at: April 27, 2026, 9:40 a.m.