Triple
T27504806
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | western Madagascar |
E694250
|
entity |
| Predicate | containsNotableSite |
P153329
|
FINISHED |
| Object |
Avenue of the Baobabs
Avenue of the Baobabs is a famous dirt road flanked by towering ancient baobab trees, forming one of Madagascar’s most iconic and photographed landscapes.
|
E1774756
|
NE FINISHED |
How this triple was built (3 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: Avenue of the Baobabs | Statement: [western Madagascar, containsNotableSite, Avenue of the Baobabs]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Avenue of the Baobabs Triple: [western Madagascar, containsNotableSite, Avenue of the Baobabs]
Generated description
Avenue of the Baobabs is a famous dirt road flanked by towering ancient baobab trees, forming one of Madagascar’s most iconic and photographed landscapes.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: containsNotableSite Context triple: [western Madagascar, containsNotableSite, Avenue of the Baobabs]
-
A.
notableSite
Indicates that a site holds particular significance, prominence, or recognition in some context.
-
B.
notableSiteFor
Indicates that a site is particularly recognized or distinguished for a specific feature, activity, event, or characteristic.
-
C.
containsNotablePlace
chosen
Indicates that one location includes within its boundaries a place that is considered notable or significant.
-
D.
notableSiteListedOn
Indicates that a notable site is recorded or referenced within a particular list, registry, or catalog.
-
E.
notableSiteType
Indicates that a site is notable specifically for being of a particular type or category (e.g., a notable example of that kind of site).
- F. None of above.
Provenance (6 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_69ef538370888190b1ddf53bb4831188 |
completed | April 27, 2026, 12:16 p.m. |
| NER | Named-entity recognition | batch_69fd2cf39b0c8190811b8a6fa9410560 |
completed | May 8, 2026, 12:23 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a12bbfacc7081909040478b658d100b |
completed | May 24, 2026, 8:51 a.m. |
| NEDg | Description generation | batch_6a12bcaf87d881908d3f629762d00254 |
completed | May 24, 2026, 8:54 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a12bd54a848819092e9265b20d16540 |
completed | May 24, 2026, 8:56 a.m. |
| PD | Predicate disambiguation | batch_69fd2ad8dd988190a9899701ba00d917 |
completed | May 8, 2026, 12:14 a.m. |
Created at: April 27, 2026, 1:13 p.m.