Triple
T25149173
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Steadfast Tin Soldier |
E630020
|
entity |
| Predicate | physicalCharacteristicOfProtagonist |
P21469
|
FINISHED |
| Object | has only one leg |
—
|
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: has only one leg | Statement: [The Steadfast Tin Soldier, physicalCharacteristicOfProtagonist, has only one leg]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: physicalCharacteristicOfProtagonist Context triple: [The Steadfast Tin Soldier, physicalCharacteristicOfProtagonist, has only one leg]
-
A.
protagonistCharacteristic
chosen
Indicates that a characteristic, trait, or defining quality is attributed to the protagonist in a narrative or scenario.
-
B.
monsterCharacteristic
Indicates that a monster possesses a particular attribute, trait, or quality.
-
C.
characterSetting
Indicates that a character is associated with, appears in, or is situated within a particular setting or environment.
-
D.
featuresCharacterWith
Indicates that one entity (such as a work or product) includes or presents a particular character as part of its content.
-
E.
primaryCharacteristics
Indicates the main defining traits or features that most fundamentally characterize an 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_69e2ff349e408190a6f4a5a66279f54d |
completed | April 18, 2026, 3:49 a.m. |
| NER | Named-entity recognition | batch_69f48b9b687881908fd87a2f5fa0b1e7 |
completed | May 1, 2026, 11:16 a.m. |
| PD | Predicate disambiguation | batch_69f4806d93dc8190b9dff4c63186faff |
completed | May 1, 2026, 10:29 a.m. |
Created at: April 18, 2026, 6:30 a.m.