Triple
T12864266
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Titi Owusu Addo |
E307675
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Titi |
E261012
|
NE 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: Titi | Statement: [Titi Owusu Addo, givenName, Titi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Titi Context triple: [Titi Owusu Addo, givenName, Titi]
-
A.
Titi
Titi is a small town in the Jelebu District of Negeri Sembilan, Malaysia, known for its rural setting and local agricultural activities.
-
B.
Titti
Titti were one of the principal Celtiberian tribes inhabiting the central Iberian Peninsula in pre-Roman times.
-
C.
Tiffy
chosen
Tiffy is a common nickname or diminutive form of the given name Tiffany.
-
D.
Zizi
Zizi is a Liberian former professional footballer best known for playing as a striker for clubs in Europe and the United States.
-
E.
Ninji
Ninji is a small, black, ninja-like creature from the Super Mario series known for its leaping attacks and appearances as a recurring enemy.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d7bdf69bc48190af6c2621f28ca351 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d9708cf6b48190886a99e04d85d348 |
completed | April 10, 2026, 9:50 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f69bb092b88190b159f1d79156cf86 |
completed | May 3, 2026, 12:49 a.m. |
Created at: April 9, 2026, 5:37 p.m.