Triple
T27308195
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paranthropus |
E689124
|
entity |
| Predicate | enamelCharacteristic |
P128829
|
FINISHED |
| Object | thick enamel on molars |
—
|
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: thick enamel on molars | Statement: [Paranthropus, enamelCharacteristic, thick enamel on molars]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: enamelCharacteristic Context triple: [Paranthropus, enamelCharacteristic, thick enamel on molars]
-
A.
distinguishingDentalFeature
Indicates that one entity has a dental characteristic that serves to differentiate it from another entity or group.
-
B.
spanCharacteristic
Indicates that one entity has a particular measurable or descriptive property that characterizes the extent, duration, or range of another entity or phenomenon.
-
C.
toothAdaptation
chosen
Indicates how an organism’s teeth are structurally or functionally modified in response to its diet, environment, or evolutionary pressures.
-
D.
dentition
Indicates the type, arrangement, or condition of teeth that an entity possesses.
-
E.
codeCharacteristic
Indicates that one piece of code possesses a specific property, feature, or quality in relation to another referenced aspect.
- 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_69ef355b931c8190a63cafaf7bcc008b |
completed | April 27, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69f627b0ae548190bbdacafe61147088 |
completed | May 2, 2026, 4:34 p.m. |
| PD | Predicate disambiguation | batch_69f620e38aec8190bb184edcdbd6da64 |
completed | May 2, 2026, 4:05 p.m. |
Created at: April 27, 2026, 11:26 a.m.